tests/test.sh exit code (0 → resolved); the classification below is post-hoc and cannot change it.List app structure
ls -la && echo "---SUBMISSION---" && ls -la submission/ && echo "---DATA---" && ls -la data/ && echo "---CHECKS---" && wc -l run_checks.py test.sh 2>/dev/null
total 117 drwxr-xr-x 4 user user 4096 Jun 30 22:11 . drwxr-xr-x 21 root root 4096 Jun 30 22:11 .. -rw-r--r-- 1 user user 15364 Jun 30 22:11 PROMPT.txt -rw-r--r-- 1 user user 5 Jun 30 22:11 agent.pid -rw-r--r-- 1 user user 0 Jun 30 22:11 agent.stderr -rw-r--r-- 1 user user 5203 Jun 30 22:11 agent_trajectory.jsonl drwxr-xr-x 2 user user 60 Jun 30 22:11 data -rw-r--r-- 1 user user 0 Jun 30 22:11 run.log -rwxr-xr-x 1 user user 76773 Jun 30 10:02 run_checks.py drwxr-xr-x 2 user user 128 Jun 30 22:11 submission -rwxr-xr-x 1 user user 804 Jun 30 10:02 test.sh -rwxr-xr-x 1 user user 629 Jun 30 10:02 timer.sh ---SUBMISSION--- total 112 drwxr-xr-x 2 user user 128 Jun 30 22:11 . drwxr-xr-x 4 user user 4096 Jun 30 22:11 .. -rw-r--r-- 1 user user 50472 Jun 30 10:02 autograd.py -rw-r--r-- 1 user user 1661 Jun 30 10:02 data.py -rw-r--r-- 1 user user 33295 Jun 30 10:02 nn.py -rw-r--r-- 1 user user 11509 Jun 30 10:02 optim.py -rw-r--r-- 1 user user 2827 Jun 30 10:02 train.py ---DATA--- total 1900 drwxr-xr-x 2 user user 60 Jun 30 22:11 . drwxr-xr-x 4 user user 4096 Jun 30 22:11 .. -rw-r--r-- 1 user user 1940490 Jun 30 10:02 train.npz ---CHECKS--- 1522 run_checks.py 18 test.sh 1540 total
/app/submission/autograd.py
1 """Reverse-mode automatic differentiation over numpy arrays. 2 3 YOU MUST IMPLEMENT EVERYTHING MARKED ``# TODO`` / ``raise NotImplementedError`` using numpy 4 ONLY. No torch/jax/tensorflow/autograd/etc. The grader's conformance suite (a) differentiates the 5 differentiable ops below with central finite differences and compares against YOUR analytic 6 backward, and (b) checks the LSQ ``fake_quant`` STE + scale gradient against the reference 7 definition, so every backward must be correct (a single wrong reduction / STE / Jacobian fails 8 the gradient checks and zeroes the reward). 9 10 A ``Tensor`` wraps one ``numpy.ndarray`` (stored as ``float64`` in ``self.data``) and records the 11 op that produced it so ``.backward()`` can accumulate ``.grad`` into every leaf. 12 13 CONTRACT (the grader builds its own reference against this exact API): 14 * ``Tensor(data, requires_grad=False)`` -- ``self.data`` is ``float64``; ``self.grad`` is None 15 until backward, then a same-shape ``float64`` array. requires_grad leaves accumulate grad. 16 * Every op returns a NEW Tensor whose ``requires_grad`` is the OR of its differentiable inputs, 17 and whose ``_backward`` closure does ``input._accum(local_grad)`` (so multiple paths add up). 18 * ``t.backward(grad=None)`` -- seeds ``grad`` (all-ones for a scalar) and walks the graph in 19 reverse topological order, calling each node's ``_backward``. Repeated backward accumulates. 20 * BROADCASTING: binary ops broadcast like numpy; the ba …[truncated 54775 chars]
/app/submission/nn.py
1 """QAT layers + a small INT2 CNN, built on YOUR autograd engine.
2
3 Implement every ``# TODO`` forward (the parameters + ``named_params``/``buffers`` naming are
4 already wired for you; you compose the autograd ops). The grader checks each layer's forward
5 against its OWN reference AND finite-difference-checks the gradients that flow through your
6 autograd, so the composition must be exactly right.
7
8 CHECKPOINT NAMING CONTRACT (the grader loads YOUR ``qat_model.npz`` into its own reference
9 QuantCNN by these exact keys/shapes -- do not rename):
10 stem.conv.weight (W0,3,3,3) | stem.conv.wq.scale (1,) | stem.bn.gamma/.beta (W0,) | stem.aq.scale (1,)
11 blocks.{i}.conv.weight (Cout,Cin,3,3) | blocks.{i}.conv.wq.scale (1,)
12 blocks.{i}.bn.gamma/.beta (Cout,) | blocks.{i}.aq.scale (1,)
13 head.weight (Cfeat,n_classes) | head.wq.scale (1,) | head.bias (n_classes,)
14 BN running stats are BUFFERS (saved alongside params, NOT trained by the optimizer, NOT audited):
15 stem.bn.running_mean/.running_var (W0,) | blocks.{i}.bn.running_mean/.running_var (Cout,)
16
17 Quantization: every conv/head WEIGHT is LSQ-quantized to a signed 2-bit grid {-2,-1,0,1} via a
18 per-tensor learnable step before use; every block activation (post-relu) is LSQ-quantized to an
19 unsigned 2-bit grid {0,1,2,3}. Conv = 3x3 same-padding cross-correlation. Linear head = x@weight+bias.
20 """
21 from __future__ import annotations
22
23 from typing import Dict, List
24
25 import numpy as n
…[truncated 35167 chars]/app/submission/optim.py
1 """Optimizers over autograd ``Tensor`` parameters.
2
3 Implement the ``# TODO`` update math. Both optimizers update ``param.data`` IN PLACE using
4 ``param.grad``. The grader runs one (and several) steps and compares your updated params against
5 its reference within a tight tolerance, so the math must be exact.
6
7 SGD (with momentum ``mu`` and coupled weight decay ``wd``):
8 g = grad + wd * param; v = mu * v + g; param -= lr * v
9
10 AdamW (DECOUPLED weight decay -- the decay is applied to the PARAM, not folded into the moments):
11 m = b1*m + (1-b1)*g; v = b2*v + (1-b2)*g^2
12 mhat = m / (1 - b1^t); vhat = v / (1 - b2^t) # t = 1-based step count
13 param -= lr * ( mhat / (sqrt(vhat) + eps) + wd * param )
14
15 PARAM GROUPS: both optimizers must accept EITHER a flat param list OR a list of
16 ``{"params": [...], "weight_decay": wd}`` dicts, so weight decay can be applied to SOME params
17 and not others. This matters for low-bit LSQ QAT: the per-tensor quantizer ``scale`` params,
18 BatchNorm gamma/beta, and biases must be EXCLUDED from weight decay. ``_normalize_groups`` and
19 ``split_decay_params`` are provided; honour the per-group weight decay in ``step``.
20 """
21 from __future__ import annotations
22
23 import math
24
25 from typing import Dict, List
26
27 import numpy as np
28
29 from autograd import Tensor
30
31
32 def split_decay_params(model) -> Dict[str, List[Tensor]]:
33 """Partition a model's named params into weight
…[truncated 11129 chars]/app/submission/data.py
1 """Image data loading + normalization + batching.
2
3 The dataset is a procedurally-generated CIFAR-style set: ``X`` is ``uint8`` (N,3,S,S) in [0,255],
4 ``y`` is the integer class label in [0, n_classes). The shipped training split is at
5 ``/app/data/train.npz``; the SEALED held-out split is regenerated by the verifier (never shipped).
6
7 Implement the ``# TODO`` bodies (numpy only). The verifier normalizes the held-out split with the
8 SAME transform, so match it exactly.
9
10 Contract:
11 load_npz(path) -> (X uint8 (N,3,S,S), y int64 (N,)) [provided]
12 normalize(X) -> float64: x = (X/255 - 0.5) / 0.25 [per-channel, the grader's transform]
13 iter_minibatches(Xn, y, batch_size, rng, shuffle=True) -> yields (xb, yb)
14 """
15 from __future__ import annotations
16
17 from typing import Tuple
18
19 import numpy as np
20
21 NORM_MEAN = 0.5
22 NORM_STD = 0.25
23
24
25 def load_npz(path: str) -> Tuple[np.ndarray, np.ndarray]:
26 d = np.load(path)
27 X = np.asarray(d["X"]).astype(np.uint8)
28 y = np.asarray(d["y"]).astype(np.int64).reshape(-1)
29 return X, y
30
31
32 def normalize(X: np.ndarray) -> np.ndarray:
33 """uint8 (N,3,S,S) -> float64, x = (X/255 - NORM_MEAN) / NORM_STD."""
34 # TODO: cast to float, scale to [0,1], subtract NORM_MEAN, divide by NORM_STD.
35 raise NotImplementedError("normalize")
36
37
38 def iter_minibatches(Xn: np.ndarray, y: np.ndarray, batch_size: int,
39 rng: np.rando
…[truncated 281 chars]/app/submission/train.py
1 """Training entry point. Implement the QAT loop, train your INT2 CNN on /app/data/train.npz, and 2 SAVE the checkpoint to /app/submission/qat_model.npz (numpy .npz of the model state_dict: every 3 param + every BN running buffer, by the nn.QuantCNN naming contract). 4 5 The grader (verify.py) will: 6 (1) run the conformance suite over your autograd/nn/optim, 7 (2) BIT-AUDIT every conv/head weight tensor in your checkpoint to <= 4 distinct float values, 8 (3) load your weights into its OWN QuantCNN and score held-out top-1 on a SEALED split. 9 10 So at SAVE time you must BAKE the quantized weights back into each ``weight`` tensor (replace it 11 with round(clip(w/s, -W_NEG, W_POS)) * s using the learned wq.scale) so the saved weights already 12 lie on the 2-bit grid and pass the audit. Reaching the top-1 floor at INT-2 needs a real recipe: 13 sensible LSQ STEP-SIZE INITIALIZATION (a default scale of 1.0 quantizes the small init weights to 14 all-zeros -> a dead network at chance), per-tensor learnable scales, weight decay EXCLUDED from the 15 scale/BN/bias params, gradient clipping, a decaying LR, and enough epochs. Naive post-training 16 rounding or under-training lands at chance. 17 18 This file is a skeleton; the loop body is yours to write. 19 """ 20 from __future__ import annotations 21 22 import argparse 23 import os 24 import sys 25 26 import numpy as np 27 28 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) 29 sys.path.insert(0, "/app") 30 3 …[truncated 1513 chars]
Find function defs in run_checks
grep -n "def \|cosine_lr\|warmup_lr\|step_lr\|multistep\|polynomial\|cosine_restarts\|linear_lr\|exponential" run_checks.py | head -80
64:def _load_module(name, path, inject=None): 84:def load_framework(root): 93:def _num_grad_input(forward, x, eps=EPS): 108:def _max_abs(a, b): 112:def _bsum(it): 119:def _imax(a, b): 124:def check_autograd_grads(fw, sb): 130: def case(name, build, shape, seed, upstream=None): 135: def wrapped(t): 193: def two_path(): 204: def loss_grad(name, lossfn, shape, seed, inttgt): 218: def norm_param(name, which, seed): 237: def conv_grad(name, which, seed): 265: def pool_grad(name, op, seed, jitter=False): 281: def bn_grad(name, dim, which, seed): 316: def layer_grad(name, make, in_shape, seed): 335: def quant_model_backprop(name, build, make_X, seed): 382: def gn_x(): 395: def gn_param(name, which, seed): 413: def cell_grad(name, make, in_shape, hid, seed, two_state=False): 424: def fwd(xv): 438: def cell_param_grad(name, make, in_shape, hid, pkey, seed, two_state=False): 450: def fwd(pv): 455: def fwd(pv): 479: def hub_grad(name, seed, scale_in, delta): 493: def kl_grad_pub(): 505: def emb_grad_pub(): 517: def conv_gen_grad_pub(name, which, seed, stride, pad, dilation, groups, Cin, cig, Cout, hw): 538: def convT_grad_pub(name, which, seed, stride, pad): 558: def pool_s_grad_pub(name, op, seed, jitter=False): 584:def check_quant_grads(fw, sb): 588: def grads(v0, s0, Qn, Qp, up): 595: def ste_indicator(name, seed, Qn, Qp, s0): 611: def scale_clip(name, seed, Qn, Q …[truncated 1442 chars]
/app/run_checks.py
584 def check_quant_grads(fw, sb):
585 ag = fw["autograd"]
586 results = []
587
588 def grads(v0, s0, Qn, Qp, up):
589 vt = ag.Tensor(v0.copy(), requires_grad=True)
590 st = ag.Tensor(np.array([s0]), requires_grad=True)
591 out = ag.fake_quant(vt, st, Qn, Qp)
592 out.backward(up.copy())
593 return np.asarray(vt.grad, np.float64), np.asarray(st.grad, np.float64), out.data.copy()
594
595 def ste_indicator(name, seed, Qn, Qp, s0):
596 try:
597 rng = np.random.default_rng(sb + seed)
598 v0 = rng.standard_normal((5, 5)) * 2.0
599 up = rng.standard_normal((5, 5))
600 gv, _, _ = grads(v0, s0, Qn, Qp, up)
601 r = v0 / s0
602 middle = (r >= -Qn) & (r <= Qp)
603 expected = up * middle
604 ok = _max_abs(gv, expected) < 1e-9 and np.all(gv[~middle] == 0.0)
605 results.append((f"quant/{name}", ok, f"err={_max_abs(gv, expected):.1e}"))
606 except Exception as e: # noqa: BLE001
607 results.append((f"quant/{name}", False, f"raised {type(e).__name__}: {e}"))
608 ste_indicator("ste_indicator_w", 60, 2, 1, 0.7)
609 ste_indicator("ste_indicator_a", 61, 0, 3, 0.5)
610
611 def scale_clip(name, seed, Qn, Qp, s0, fill, bound):
612 try:
613 v0 = np.full((4, 4), fill)
614 up = np.ones((4, 4))
615 _, gs, _ = grads(v0, s0, Qn, Qp, up)
616 gscale
…[truncated 11003 chars]Locate optim/integration/data checks
grep -n "def check_optim\|def check_integration\|def check_data" run_checks.py
1106:def check_optim(fw, sb): 1346:def check_integration(fw, sb): 1422:def check_data(fw, sb):
/app/run_checks.py
1106 def check_optim(fw, sb):
1107 ag = fw["autograd"]
1108 opt = fw["optim"]
1109 T = ag.Tensor
1110 results = []
1111
1112 def mk(seed):
1113 rng = np.random.default_rng(seed)
1114 return [T(rng.standard_normal((4, 3)), requires_grad=True), T(rng.standard_normal(3), requires_grad=True)]
1115
1116 def run(name, opt_fn, ref_step, nsteps, gseed):
1117 try:
1118 ps = mk(sb + 500)
1119 ref = [p.data.copy() for p in ps]
1120 o = opt_fn(ps)
1121 st = {}
1122 for s in range(nsteps):
1123 grng = np.random.default_rng(gseed + s)
1124 grads = [grng.standard_normal(p.data.shape) for p in ps]
1125 for p, g in zip(ps, grads):
1126 p.grad = g.copy()
1127 o.step()
1128 ref = [ref_step(i, ref[i], grads[i].copy(), s + 1, st) for i in range(len(ps))]
1129 err = max(_max_abs(p.data, ref[i]) for i, p in enumerate(ps))
1130 results.append((f"optim/{name}", err < TOL_OPT, f"max_abs={err:.1e}"))
1131 except Exception as e: # noqa: BLE001
1132 results.append((f"optim/{name}", False, f"raised {type(e).__name__}: {e}"))
1133
1134 def sgd_step(lr, mu, wd):
1135 def f(i, p, g, t, st):
1136 v = st.get(("v", i), np.zeros_like(p))
1137 g = g + wd * p
1138 v = mu * v + g
1139 st[("v", i)] = v
114
…[truncated 11079 chars]/app/run_checks.py
1346 def check_integration(fw, sb):
1347 ag = fw["autograd"]
1348 nn = fw["nn"]
1349 opt = fw["optim"]
1350 results = []
1351
1352 def init_scales(m):
1353 nps = m.named_params()
1354 for nm, p in nps.items():
1355 if nm.endswith("wq.scale"):
1356 wkey = nm[:-len("wq.scale")] + "weight"
1357 p.data[...] = _imax(2.0 * float(np.mean(np.abs(nps[wkey].data))), 1e-2)
1358 elif nm.endswith("aq.scale"):
1359 p.data[...] = 1.0
1360
1361 def overfit_loss(m, opt_build, X, y, nsteps):
1362 # repeatedly train on ONE fixed (X, y) batch: a correct forward+backward+optimizer drives
1363 # the loss DOWN on a memorizable batch. A broken backward keeps it flat/NaN.
1364 m.set_training(True)
1365 g = opt.split_decay_params(m)
1366 o = opt_build(g)
1367 losses = []
1368 for _ in range(nsteps):
1369 loss = ag.cross_entropy(m(X), y)
1370 o.zero_grad(); loss.backward(); opt.clip_grad_norm(m.params(), 2.0); o.step()
1371 losses.append(float(loss.data))
1372 return losses
1373
1374 def qcnn_run():
1375 m = nn.QuantCNN(6, widths=(8, 16), seed=sb + 5)
1376 init_scales(m)
1377 rng = np.random.default_rng(sb)
1378 X = rng.standard_normal((8, 3, 16, 16)); y = rng.integers(0, 6, size=8)
1379 return overfit_loss(m, lambda g: opt.Adam(
1380 [
…[truncated 6566 chars]/app/run_checks.py
1 #!/usr/bin/env python3 2 """PUBLIC component check runner for the from-scratch numpy QAT framework. 3 4 Run this AS OFTEN AS YOU LIKE while you implement, to get a per-check progress signal: 5 6 python3 /app/run_checks.py # check the framework in /app/submission 7 python3 /app/run_checks.py --submission /some/dir 8 python3 /app/run_checks.py --only autograd_grads # run one milestone 9 python3 /app/run_checks.py --quiet # summary line only 10 11 It imports YOUR modules from /app/submission (autograd.py / nn.py / optim.py / data.py), exactly as 12 the grader does, and runs a PUBLIC portion of the component conformance suite, printing a clear 13 per-check report so you can implement -> run -> read failures -> fix -> repeat. 14 15 HOW THIS RELATES TO YOUR GRADE 16 ------------------------------ 17 This runner is a DEBUGGING AID, not the grader. It checks YOUR framework against references it can 18 compute on its own: 19 * autograd_grads : central FINITE-DIFFERENCE of YOUR forward vs YOUR analytic backward, for every 20 differentiable op + the domain ops (conv2d/avgpool2d/maxpool2d/batchnorm2d/ 21 batchnorm1d/layernorm) + end-to-end through the full QuantCNN / QuantMLP. 22 * quant_grads : the LSQ fake_quant STE indicator + scale-gradient CLIP RULES (the exact 23 structural identities the straight-through estimator must satisfy). 24 * nn_forward : …[truncated 3964 chars]
/app/run_checks.py
124 def check_autograd_grads(fw, sb):
125 ag = fw["autograd"]
126 nn = fw["nn"]
127 T = ag.Tensor
128 results = []
129
130 def case(name, build, shape, seed, upstream=None):
131 try:
132 rng = np.random.default_rng(sb + seed)
133 x0 = rng.standard_normal(shape)
134
135 def wrapped(t):
136 o = build(t)
137 return ag.mul(o, T(upstream)) if upstream is not None else o
138 t = T(x0.copy(), requires_grad=True)
139 ag.sum(wrapped(t)).backward()
140 gan = np.asarray(t.grad, np.float64)
141 gnum = _num_grad_input(lambda xv: wrapped(T(xv)).data, x0.copy())
142 err = _max_abs(gan, gnum)
143 results.append((f"grad/{name}", err < TOL_GRAD, f"max_abs={err:.2e}"))
144 except Exception as e: # noqa: BLE001
145 results.append((f"grad/{name}", False, f"raised {type(e).__name__}: {e}"))
146
147 # element-wise binary
148 case("add_bcast", lambda t: ag.add(t, T(np.arange(t.shape[-1], dtype=float) + 1.0)), (4, 5), 1)
149 case("sub_bcast", lambda t: ag.sub(t, T(np.arange(t.shape[-1], dtype=float) + 1.0)), (4, 5), 2)
150 case("mul_bcast", lambda t: ag.mul(t, T(np.arange(t.shape[-1], dtype=float) + 1.0)), (4, 5), 3)
151 case("div", lambda t: ag.div(t, T(np.full((4, 5), 2.0))), (4, 5), 4)
152 case("div_denom", lambda t: ag.div(T(np.full((4, 5), 3.0)), ag.add(t, T(5.0))), (4, 5), 5)
153
…[truncated 27040 chars]/app/submission/autograd.py
TODO: implement the topological walk + seeding. (The per-op ``_backward`` closures do the
local accumulation; here you only orchestrate the order + seed ``self.grad``.)
"""
raise NotImplementedError("Tensor.backward") TODO: implement the topological walk + seeding. (The per-op ``_backward`` closures do the
local accumulation; here you only orchestrate the order + seed ``self.grad``.)
"""
topo: List["Tensor"] = []
visited = set()
def build(t):
if id(t) in visited:
return
visited.add(id(t))
for p in t._parents:
build(p)
topo.append(t)
build(self)
if grad is None:
grad = np.ones_like(self.data)
self._accum(_as_f64(grad))
for t in reversed(topo):
t._backward()The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("add backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(_unbroadcast(g, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(g, b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("sub backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(_unbroadcast(g, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(-g, b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("mul backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(_unbroadcast(g * b.data, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(g * a.data, b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("div backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(_unbroadcast(g / b.data, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(-g * a.data / (b.data ** 2), b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("power backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * p * (a.data ** (p - 1)))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("maximum backward") # TODO def _bw():
g = out.grad
if g is None:
return
ga = np.where(a.data > b.data, 1.0, np.where(a.data == b.data, 0.5, 0.0))
if a.requires_grad:
a._accum(_unbroadcast(g * ga, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(g * (1.0 - ga), b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("minimum backward") # TODO def _bw():
g = out.grad
if g is None:
return
ga = np.where(a.data < b.data, 1.0, np.where(a.data == b.data, 0.5, 0.0))
if a.requires_grad:
a._accum(_unbroadcast(g * ga, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(g * (1.0 - ga), b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("where backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(_unbroadcast(np.where(c, g, 0.0), a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(np.where(c, 0.0, g), b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("exp backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * out.data)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("log backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g / a.data)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("sqrt backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * 0.5 / out.data)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("abs backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * np.sign(a.data))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("clip backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
mask = (a.data > lo) & (a.data < hi)
a._accum(g * mask)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("sum backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
if axis is not None and not keepdims:
ax = axis if isinstance(axis, tuple) else (axis,)
for a_ in sorted(a_ % a.data.ndim for a_ in ax):
g2 = np.expand_dims(g2, a_)
a._accum(np.broadcast_to(g2, a.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("mean backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
if axis is None:
N = a.data.size
else:
ax = axis if isinstance(axis, tuple) else (axis,)
if not keepdims:
for a_ in sorted(a_ % a.data.ndim for a_ in ax):
g2 = np.expand_dims(g2, a_)
N = 1
for a_ in ax:
N *= a.data.shape[a_]
a._accum(np.broadcast_to(g2, a.data.shape) / N)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("max backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
of = out.data
if axis is not None and not keepdims:
ax = axis if isinstance(axis, tuple) else (axis,)
for a_ in sorted(a_ % a.data.ndim for a_ in ax):
g2 = np.expand_dims(g2, a_)
of = np.expand_dims(of, a_)
mask = (a.data == of)
cnt = mask.sum(axis=axis, keepdims=True)
a._accum(mask * g2 / cnt)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("min backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
of = out.data
if axis is not None and not keepdims:
ax = axis if isinstance(axis, tuple) else (axis,)
for a_ in sorted(a_ % a.data.ndim for a_ in ax):
g2 = np.expand_dims(g2, a_)
of = np.expand_dims(of, a_)
mask = (a.data == of)
cnt = mask.sum(axis=axis, keepdims=True)
a._accum(mask * g2 / cnt)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("concat backward") # TODO def _bw():
g = out.grad
if g is None:
return
idx = 0
for t in ts:
sz = t.data.shape[axis]
sl = [slice(None)] * g.ndim
sl[axis] = slice(idx, idx + sz)
if t.requires_grad:
t._accum(g[tuple(sl)])
idx += szThe file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("stack backward") # TODO def _bw():
g = out.grad
if g is None:
return
for i, t in enumerate(ts):
sl = [slice(None)] * g.ndim
sl[axis] = i
if t.requires_grad:
t._accum(g[tuple(sl)])The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("transpose backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
if axes is None:
a._accum(np.transpose(g))
else:
inv = np.argsort(axes)
a._accum(np.transpose(g, tuple(inv)))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("reshape backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g.reshape(a.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("getitem backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
gz = np.zeros_like(a.data)
np.add.at(gz, idx, g)
a._accum(gz)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("matmul backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
da = g @ np.swapaxes(b.data, -1, -2)
a._accum(_unbroadcast(da, a.data.shape))
if b.requires_grad:
db = np.swapaxes(a.data, -1, -2) @ g
b._accum(_unbroadcast(db, b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("relu backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * (a.data > 0.0))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("leaky_relu backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * np.where(a.data > 0.0, 1.0, slope))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("sigmoid backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * out.data * (1.0 - out.data))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("tanh backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * (1.0 - out.data ** 2))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("gelu backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
pdf = np.exp(-a.data * a.data / 2.0) / np.sqrt(2.0 * np.pi)
a._accum(g * (cdf + a.data * pdf))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("softmax backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
s = out.data
a._accum(s * (g - (g * s).sum(axis=axis, keepdims=True)))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("log_softmax backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
sm = np.exp(out.data)
a._accum(g - sm * g.sum(axis=axis, keepdims=True))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("cross_entropy backward") # TODO def _bw():
g = out.grad
if g is None:
return
if logits.requires_grad:
sm = np.exp(logp)
sm[np.arange(n), t] -= 1.0
logits._accum(g * sm / n)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("mse_loss backward") # TODO def _bw():
g = out.grad
if g is None:
return
if pred.requires_grad:
pred._accum(g * 2.0 * (pred.data - tgt) / pred.data.size)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("layernorm backward") # TODO def _bw():
g = out.grad
if g is None:
return
axes = tuple(range(g.ndim - 1))
if gamma.requires_grad:
gamma._accum((g * xhat).sum(axis=axes))
if beta.requires_grad:
beta._accum(g.sum(axis=axes))
if x.requires_grad:
gx = g * gamma.data
dx = inv / D * (D * gx - gx.sum(axis=-1, keepdims=True)
- xhat * (gx * xhat).sum(axis=-1, keepdims=True))
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("conv2d backward") # TODO (dW, dbias, dx via _col2im) def _bw():
g = out.grad
if g is None:
return
gm = g.reshape(N, Cout, OH * OW)
if weight.requires_grad:
dW = np.einsum("nop,ncp->oc", gm, cols).reshape(Cout, Cin, KH, KW)
weight._accum(dW)
if has_bias and bias.requires_grad:
bias._accum(gm.sum(axis=(0, 2)))
if x.requires_grad:
dcols = np.einsum("oc,nop->ncp", Wm, gm)
dxp = _col2im(dcols, xp.shape, KH, KW, stride, OH, OW)
if pad > 0:
dx = dxp[:, :, pad:pad + H, pad:pad + W]
else:
dx = dxp
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("avgpool2d backward") # TODO def _bw():
g = out.grad
if g is None:
return
if x.requires_grad:
gg = (g / (k * k))[:, :, :, None, :, None]
block = np.broadcast_to(gg, (N, C, OH, k, OW, k))
dx = np.zeros_like(x.data)
dx[:, :, :OH * k, :OW * k] = block.reshape(N, C, OH * k, OW * k)
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("maxpool2d backward") # TODO def _bw():
g = out.grad
if g is None:
return
if x.requires_grad:
xr2 = x.data[:, :, :OH * k, :OW * k].reshape(N, C, OH, k, OW, k)
m = out.data[:, :, :, None, :, None]
mask = (xr2 == m)
cnt = mask.sum(axis=(3, 5), keepdims=True)
gg = g[:, :, :, None, :, None]
block = mask * gg / cnt
dx = np.zeros_like(x.data)
dx[:, :, :OH * k, :OW * k] = block.reshape(N, C, OH * k, OW * k)
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("batchnorm2d backward") # TODO def _bw():
g = out.grad
if g is None:
return
if gamma.requires_grad:
gamma._accum((g * xhat).sum(axis=(0, 2, 3)))
if beta.requires_grad:
beta._accum(g.sum(axis=(0, 2, 3)))
if x.requires_grad:
gx = g * g_
if training:
sgx = gx.sum(axis=(0, 2, 3), keepdims=True)
sgxx = (gx * xhat).sum(axis=(0, 2, 3), keepdims=True)
dx = inv / M * (M * gx - sgx - xhat * sgxx)
else:
dx = gx * inv
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("fake_quant backward (STE + LSQ scale gradient)") # TODO def _bw():
g = out.grad
if g is None:
return
mid = (r >= Qn) & (r <= Qp)
if v.requires_grad:
v._accum(g * mid)
if scale.requires_grad:
below = r < Qn
above = r > Qp
d = np.where(below, Qn, np.where(above, Qp, np.round(r) - r))
ds = np.sum(g * d) * grad_scale
scale._accum(np.asarray(ds, dtype=np.float64).reshape(scale.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("square backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * 2.0 * a.data)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("rsqrt backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * -0.5 * a.data ** (-1.5))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("reciprocal backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(-g * out.data * out.data)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("var backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
if axis is None:
N = a.data.size
else:
ax = axis if isinstance(axis, tuple) else (axis,)
if not keepdims:
for a_ in sorted(a_ % a.data.ndim for a_ in ax):
g2 = np.expand_dims(g2, a_)
N = 1
for a_ in ax:
N *= a.data.shape[a_]
a._accum(g2 * (2.0 / N) * xc)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("std backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
if axis is None:
N = a.data.size
else:
ax = axis if isinstance(axis, tuple) else (axis,)
if not keepdims:
for a_ in sorted(a_ % a.data.ndim for a_ in ax):
g2 = np.expand_dims(g2, a_)
N = 1
for a_ in ax:
N *= a.data.shape[a_]
a._accum(g2 * xc / (N * sd))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("gather backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
gz = np.zeros_like(a.data)
grids = list(np.ogrid[tuple(slice(0, s) for s in out.data.shape)])
grids[axis] = idx
np.add.at(gz, tuple(grids), g)
a._accum(gz)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("pad2d backward") # TODO def _bw():
g = out.grad
if g is None:
return
if x.requires_grad:
if pad > 0:
x._accum(g[:, :, pad:-pad, pad:-pad])
else:
x._accum(g)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("softplus backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
with np.errstate(over="ignore"):
sig = 1.0 / (1.0 + np.exp(-beta * a.data))
a._accum(g * sig)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("silu backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * (sig + a.data * sig * (1.0 - sig)))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("mish backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
th = np.tanh(sp)
with np.errstate(over="ignore"):
sig = 1.0 / (1.0 + np.exp(-x))
a._accum(g * (th + x * (1.0 - th * th) * sig))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("elu backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(g * np.where(x > 0.0, 1.0, alpha * np.exp(np.minimum(x, 0.0))))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("hardtanh backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
mask = (a.data > lo) & (a.data < hi)
a._accum(g * mask)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("hardsigmoid backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
mask = (z > 0.0) & (z < 1.0)
a._accum(g * mask / 6.0)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("groupnorm backward") # TODO def _bw():
g = out.grad
if g is None:
return
if gamma.requires_grad:
gamma._accum((g * xhat).sum(axis=(0, 2, 3)))
if beta.requires_grad:
beta._accum(g.sum(axis=(0, 2, 3)))
if x.requires_grad:
M = cg * H * W
gx = (g * gamma.data.reshape(1, C, 1, 1)).reshape(N, G, M)
xh = xhat.reshape(N, G, M)
sgx = gx.sum(axis=2, keepdims=True)
sgxx = (gx * xh).sum(axis=2, keepdims=True)
dxg = inv / M * (M * gx - sgx - xh * sgxx)
x._accum(dxg.reshape(N, C, H, W))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("fake_quant_per_channel backward (STE + per-channel scale grad)") # TODO def _bw():
g = out.grad
if g is None:
return
mid = (r >= Qn) & (r <= Qp)
if v.requires_grad:
v._accum(g * mid)
if scale.requires_grad:
below = r < Qn
above = r > Qp
d = np.where(below, Qn, np.where(above, Qp, np.round(r) - r))
axes = tuple(i for i in range(g.ndim) if i != axis)
scale._accum((g * d).sum(axis=axes) * grad_scale)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("fake_quant_affine backward (STE + scale grad on shifted grid)") # TODO def _bw():
g = out.grad
if g is None:
return
mid = (r >= Qn) & (r <= Qp)
if v.requires_grad:
v._accum(g * mid)
if scale.requires_grad:
lower = r < Qn
upper = r > Qp
middle = ~(lower | upper)
d = np.where(middle, (q - z) - (r - z), np.where(lower, Qn - z, Qp - z))
ds = np.sum(g * d) * grad_scale
scale._accum(np.asarray(ds, dtype=np.float64).reshape(scale.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("cumsum backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
rc = np.flip(np.cumsum(np.flip(g, axis=axis), axis=axis), axis=axis)
a._accum(rc)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("flip backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
a._accum(np.flip(g, axis=axis))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("logsumexp backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
g2 = np.asarray(g)
if not keepdims:
g2 = np.expand_dims(g2, axis)
a._accum(sm * g2)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("logaddexp backward") # TODO def _bw():
g = out.grad
if g is None:
return
wa = np.exp(a.data - out_data)
wb = np.exp(b.data - out_data)
if a.requires_grad:
a._accum(_unbroadcast(g * wa, a.data.shape))
if b.requires_grad:
b._accum(_unbroadcast(g * wb, b.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("l2_normalize backward") # TODO def _bw():
g = out.grad
if g is None:
return
if a.requires_grad:
yy = out.data
proj = (yy * g).sum(axis=axis, keepdims=True)
a._accum((g - yy * proj) / nrm)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("rms_norm backward") # TODO def _bw():
g = out.grad
if g is None:
return
if gamma.requires_grad:
axes = tuple(range(g.ndim - 1))
gamma._accum((g * xhat).sum(axis=axes))
if x.requires_grad:
gg = g * gamma.data
s = (gg * xd).sum(axis=-1, keepdims=True)
dx = inv * gg - (xd * inv ** 3 / D) * s
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("instance_norm backward") # TODO def _bw():
g = out.grad
if g is None:
return
if gamma.requires_grad:
gamma._accum((g * xhat).sum(axis=(0, 2, 3)))
if beta.requires_grad:
beta._accum(g.sum(axis=(0, 2, 3)))
if x.requires_grad:
gx = (g * gamma.data.reshape(1, C, 1, 1)).reshape(N, C, M)
xh = xhat.reshape(N, C, M)
sgx = gx.sum(axis=2, keepdims=True)
sgxx = (gx * xh).sum(axis=2, keepdims=True)
dx = inv / M * (M * gx - sgx - xh * sgxx)
x._accum(dx.reshape(N, C, H, W))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("huber_loss backward") # TODO def _bw():
g = out.grad
if g is None:
return
if pred.requires_grad:
grad_in = np.where(quad, diff, delta * np.sign(diff))
pred._accum(g * grad_in / n)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("kl_div backward") # TODO def _bw():
g = out.grad
if g is None:
return
if log_p.requires_grad:
log_p._accum(g * (-q) / n)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("embedding backward") # TODO def _bw():
g = out.grad
if g is None:
return
if weight.requires_grad:
gz = np.zeros_like(weight.data)
np.add.at(gz, idx, g)
weight._accum(gz)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("conv2d_gen backward (grouped/dilated dW/db/dx)") # TODO def _bw():
g = out.grad
if g is None:
return
g_full = g.reshape(N, Cout, OH * OW)
gg = g_full.reshape(N, groups, cog, OH * OW)
if weight.requires_grad:
dW = np.einsum("ngop,ngcp->goc", gg, cols_g).reshape(Cout, cig, KH, KW)
weight._accum(dW)
if has_bias and bias.requires_grad:
bias._accum(g_full.sum(axis=(0, 2)))
if x.requires_grad:
dcols_g = np.einsum("goc,ngop->ngcp", Wm, gg)
dcols = dcols_g.reshape(N, groups * cig * KH * KW, OH * OW)
dxp = _col2im_dil(dcols, xp.shape, KH, KW, stride, dilation, OH, OW)
if pad > 0:
dx = dxp[:, :, pad:pad + H, pad:pad + W]
else:
dx = dxp
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("conv_transpose2d backward") # TODO def _bw():
g = out.grad
if g is None:
return
if has_bias and bias.requires_grad:
bias._accum(g.sum(axis=(0, 2, 3)))
if pad > 0:
gfull = np.zeros((N, Cout, OHf, OWf), dtype=np.float64)
gfull[:, :, pad:OHf - pad, pad:OWf - pad] = g
else:
gfull = g
gcontrib = np.empty((N, Cout, H, W, KH, KW), dtype=np.float64)
for i in range(KH):
for j in range(KW):
gcontrib[:, :, :, :, i, j] = gfull[:, :, i:i + stride * H:stride, j:j + stride * W:stride]
if x.requires_grad:
dx = np.einsum("noijKL,coKL->ncij", gcontrib, Wm)
x._accum(dx)
if weight.requires_grad:
dW = np.einsum("ncij,noijKL->coKL", xd, gcontrib)
weight._accum(dW)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("avgpool2d_s backward") # TODO def _bw():
g = out.grad
if g is None:
return
if x.requires_grad:
dxp = np.zeros((N, C, Hp, Wp), dtype=np.float64)
for oi in range(OH):
for oj in range(OW):
dxp[:, :, oi * stride:oi * stride + k, oj * stride:oj * stride + k] += \
(g[:, :, oi, oj] / (k * k))[:, :, None, None]
if pad > 0:
dx = dxp[:, :, pad:pad + H, pad:pad + W]
else:
dx = dxp
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("maxpool2d_s backward") # TODO def _bw():
g = out.grad
if g is None:
return
if x.requires_grad:
dxp = np.zeros((N, C, Hp, Wp), dtype=np.float64)
rows = np.arange(N)[:, None]
cols = np.arange(C)[None, :]
for oi in range(OH):
for oj in range(OW):
ii = oi * stride + argi[:, :, oi, oj]
jj = oj * stride + argj[:, :, oi, oj]
np.add.at(dxp, (rows, cols, ii, jj), g[:, :, oi, oj])
if pad > 0:
dx = dxp[:, :, pad:pad + H, pad:pad + W]
else:
dx = dxp
x._accum(dx)The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/autograd.py
def _bw():
raise NotImplementedError("fake_quant_lsq_plus backward (STE v-grad + beta-grad + LSQ scale grad)") # TODO def _bw():
g = out.grad
if g is None:
return
mid = (r >= Qn) & (r <= Qp)
if v.requires_grad:
v._accum(g * mid)
if beta.requires_grad:
db = np.sum(g * (~mid))
beta._accum(np.asarray(db, dtype=np.float64).reshape(beta.data.shape))
if scale.requires_grad:
below = r < Qn
above = r > Qp
d = np.where(mid, np.round(np.clip(r, Qn, Qp)) - r, np.where(below, Qn, Qp))
ds = np.sum(g * d) * grad_scale
scale._accum(np.asarray(ds, dtype=np.float64).reshape(scale.data.shape))The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
Check remaining stubs in autograd
grep -n "NotImplementedError\|# TODO" submission/autograd.py
3:YOU MUST IMPLEMENT EVERYTHING MARKED ``# TODO`` / ``raise NotImplementedError`` using numpy
/app/submission/optim.py
def step(self):
# TODO: SGD(+momentum, +per-group weight decay) update. Iterate self._groups; for each
# group use wd = self.weight_decay if override is None else override; keep a momentum
# buffer per parameter (self._v is indexed in self.params order).
raise NotImplementedError("SGD.step") def step(self):
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._v[i] = self.momentum * self._v[i] + g
p.data -= self.lr * self._v[i]
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: AdamW with bias correction + DECOUPLED, per-group weight decay (see docstring).
raise NotImplementedError("AdamW.step") def step(self):
self.t += 1
t = self.t
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad
self._m[i] = self.b1 * self._m[i] + (1 - self.b1) * g
self._v[i] = self.b2 * self._v[i] + (1 - self.b2) * (g * g)
mhat = self._m[i] / (1 - self.b1 ** t)
vhat = self._v[i] / (1 - self.b2 ** t)
p.data -= self.lr * (mhat / (np.sqrt(vhat) + self.eps) + wd * p.data)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: Adam with bias correction + COUPLED, per-group weight decay (see docstring).
raise NotImplementedError("Adam.step") def step(self):
self.t += 1
t = self.t
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._m[i] = self.b1 * self._m[i] + (1 - self.b1) * g
self._v[i] = self.b2 * self._v[i] + (1 - self.b2) * (g * g)
mhat = self._m[i] / (1 - self.b1 ** t)
vhat = self._v[i] / (1 - self.b2 ** t)
p.data -= self.lr * mhat / (np.sqrt(vhat) + self.eps)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: RMSprop update with per-group weight decay (see docstring).
raise NotImplementedError("RMSprop.step") def step(self):
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._s[i] = self.alpha * self._s[i] + (1 - self.alpha) * (g * g)
p.data -= self.lr * g / (np.sqrt(self._s[i]) + self.eps)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: Adagrad update with per-group weight decay (see docstring).
raise NotImplementedError("Adagrad.step") def step(self):
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._s[i] = self._s[i] + g * g
p.data -= self.lr * g / (np.sqrt(self._s[i]) + self.eps)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: Lion update with per-group (decoupled) weight decay (see docstring).
raise NotImplementedError("Lion.step") def step(self):
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad
upd = np.sign(self.b1 * self._m[i] + (1 - self.b1) * g)
p.data -= self.lr * (upd + wd * p.data)
self._m[i] = self.b2 * self._m[i] + (1 - self.b2) * g
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: implement the Adamax update honouring per-group weight decay.
raise NotImplementedError("Adamax.step") def step(self):
self.t += 1
t = self.t
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._m[i] = self.b1 * self._m[i] + (1 - self.b1) * g
self._u[i] = np.maximum(self.b2 * self._u[i], np.abs(g))
p.data -= (self.lr / (1 - self.b1 ** t)) * self._m[i] / (self._u[i] + self.eps)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: implement the NAdam update honouring per-group weight decay.
raise NotImplementedError("NAdam.step") def step(self):
self.t += 1
t = self.t
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._m[i] = self.b1 * self._m[i] + (1 - self.b1) * g
self._v[i] = self.b2 * self._v[i] + (1 - self.b2) * (g * g)
mhat = (self.b1 * self._m[i] / (1 - self.b1 ** (t + 1))
+ (1 - self.b1) * g / (1 - self.b1 ** t))
vhat = self._v[i] / (1 - self.b2 ** t)
p.data -= self.lr * mhat / (np.sqrt(vhat) + self.eps)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: implement the Adadelta update honouring per-group weight decay.
raise NotImplementedError("Adadelta.step") def step(self):
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._s[i] = self.rho * self._s[i] + (1 - self.rho) * (g * g)
delta = np.sqrt(self._d[i] + self.eps) / np.sqrt(self._s[i] + self.eps) * g
p.data -= self.lr * delta
self._d[i] = self.rho * self._d[i] + (1 - self.rho) * (delta * delta)
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
def step(self):
# TODO: implement the Nesterov-SGD update honouring per-group weight decay.
raise NotImplementedError("NesterovSGD.step") def step(self):
i = 0
for grp, override in self._groups:
wd = self.weight_decay if override is None else override
for p in grp:
if p.grad is not None:
g = p.grad + wd * p.data
self._v[i] = self.momentum * self._v[i] + g
p.data -= self.lr * (g + self.momentum * self._v[i])
i += 1The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
# TODO: compute the global L2 norm over all param grads; scale in place if it exceeds max_norm.
raise NotImplementedError("clip_grad_norm") total = 0.0
for p in params:
if p.grad is not None:
total += float((p.grad ** 2).sum())
total = math.sqrt(total)
if total > max_norm:
scale = max_norm / (total + 1e-6)
for p in params:
if p.grad is not None:
p.grad = p.grad * scale
return totalThe file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
``base_lr`` to ``min_lr`` over the remaining (total - warmup) steps. Return the LR at ``step``."""
# TODO
raise NotImplementedError("cosine_lr") ``base_lr`` to ``min_lr`` over the remaining (total - warmup) steps. Return the LR at ``step``."""
if warmup > 0 and step < warmup:
return base_lr * (step + 1) / warmup
prog = min(1.0, max(0.0, (step - warmup) / max(1, total - warmup)))
return min_lr + 0.5 * (base_lr - min_lr) * (1 + math.cos(math.pi * prog))The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
constant ``base_lr``."""
# TODO
raise NotImplementedError("warmup_lr") constant ``base_lr``."""
if step < warmup:
return base_lr * (step + 1) / warmup
return base_lrThe file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
"""Step decay: base_lr * gamma ** (step // step_size)."""
# TODO
raise NotImplementedError("step_lr") """Step decay: base_lr * gamma ** (step // step_size)."""
return base_lr * gamma ** (step // step_size)The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
"""Exponential decay: base_lr * gamma ** step."""
# TODO
raise NotImplementedError("exponential_lr") """Exponential decay: base_lr * gamma ** step."""
return base_lr * gamma ** stepThe file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
"""Polynomial decay: min_lr + (base_lr - min_lr) * (1 - step/total)^power (clamped at total)."""
# TODO
raise NotImplementedError("polynomial_lr") """Polynomial decay: min_lr + (base_lr - min_lr) * (1 - step/total)^power (clamped at total)."""
prog = min(1.0, max(0.0, step / total))
return min_lr + (base_lr - min_lr) * ((1 - prog) ** power)The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
"""Linear decay from base_lr to min_lr over ``total`` steps, then constant at min_lr."""
# TODO
raise NotImplementedError("linear_lr") """Linear decay from base_lr to min_lr over ``total`` steps, then constant at min_lr."""
return base_lr + (min_lr - base_lr) * min(1.0, max(0.0, step / total))The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
"""base_lr * gamma^(number of milestones <= step)."""
# TODO
raise NotImplementedError("multistep_lr") """base_lr * gamma^(number of milestones <= step)."""
return base_lr * gamma ** sum(1 for m in milestones if step >= m)The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/optim.py
"""Cosine annealing with warm restarts of fixed ``period`` (cosine within each period)."""
# TODO
raise NotImplementedError("cosine_restarts_lr") """Cosine annealing with warm restarts of fixed ``period`` (cosine within each period)."""
t = step % period
return min_lr + 0.5 * (base_lr - min_lr) * (1 + math.cos(math.pi * (t / period)))The file /app/submission/optim.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/data.py
# TODO: cast to float, scale to [0,1], subtract NORM_MEAN, divide by NORM_STD.
raise NotImplementedError("normalize")return (X.astype(np.float64) / 255.0 - NORM_MEAN) / NORM_STD
The file /app/submission/data.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/data.py
# TODO: optionally shuffle an index array, then yield contiguous batch_size slices of it.
raise NotImplementedError("iter_minibatches") n = Xn.shape[0]
idx = np.arange(n)
if shuffle:
rng.shuffle(idx)
for start in range(0, n, batch_size):
sel = idx[start:start + batch_size]
yield Xn[sel], y[sel]The file /app/submission/data.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: y = x @ weight (+ bias). Use ag.matmul / ag.add.
raise NotImplementedError("Linear.forward") y = ag.matmul(x, self.weight)
if self.bias is not None:
y = ag.add(y, self.bias)
return yThe file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: out = x + fc2(gelu(fc1(x)))
raise NotImplementedError("MLP.forward")return ag.add(x, self.fc2(ag.gelu(self.fc1(x))))
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.layernorm(x, self.gamma, self.beta, self.eps)
raise NotImplementedError("LayerNorm.forward")return ag.layernorm(x, self.gamma, self.beta, self.eps)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.conv2d(x, self.weight, bias=self.bias, stride=self.stride, pad=self.padding)
raise NotImplementedError("Conv2d.forward")return ag.conv2d(x, self.weight, bias=self.bias, stride=self.stride, pad=self.padding)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.maxpool2d(x, self.k)
raise NotImplementedError("MaxPool2d.forward")return ag.maxpool2d(x, self.k)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.avgpool2d(x, self.k)
raise NotImplementedError("AvgPool2d.forward")return ag.avgpool2d(x, self.k)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.fake_quant(w, self.scale, W_NEG, W_POS)
raise NotImplementedError("WeightQuant.quant")return ag.fake_quant(w, self.scale, W_NEG, W_POS)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.fake_quant(x, self.scale, A_NEG, A_POS)
raise NotImplementedError("ActQuant.forward")return ag.fake_quant(x, self.scale, A_NEG, A_POS)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: ag.batchnorm2d(x, gamma, beta, eps, running_mean, running_var, momentum, training)
raise NotImplementedError("BatchNorm2d.forward") return ag.batchnorm2d(x, self.gamma, self.beta, self.eps,
running_mean=self.running_mean, running_var=self.running_var,
momentum=self.momentum, training=self.training)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
Check batchnorm1d presence
grep -n "batchnorm1d\|def conv_transpose2d\|def avgpool2d_s" submission/autograd.py
1764:def conv_transpose2d(x, weight, bias=None, stride=1, pad=0) -> Tensor: 1817:def avgpool2d_s(x, k, stride=None, pad=0) -> Tensor:
/app/run_checks.py
841 def layernorm_stats():
842 x = np.random.default_rng(sb + 14).standard_normal((4, 16))
843 y = ag.layernorm(T(x), T(np.ones(16)), T(np.zeros(16))).data
844 return _max_abs(y.mean(-1), np.zeros(4)) < 1e-4 and _max_abs(y.var(-1), np.ones(4)) < 1e-2, ""
845
846 def bn2d_stats():
847 x = np.random.default_rng(sb + 15).standard_normal((8, 3, 4, 4))
848 y = ag.batchnorm2d(T(x), T(np.ones(3)), T(np.zeros(3)), training=True).data
849 return _max_abs(y.mean((0, 2, 3)), np.zeros(3)) < 1e-4 and _max_abs(y.var((0, 2, 3)), np.ones(3)) < 1e-2, ""
850
851 def bn1d_stats():
852 x = np.random.default_rng(sb + 16).standard_normal((16, 5))
853 y = ag.batchnorm1d(T(x), T(np.ones(5)), T(np.zeros(5)), training=True).data
854 return _max_abs(y.mean(0), np.zeros(5)) < 1e-4 and _max_abs(y.var(0), np.ones(5)) < 1e-2, ""
855
856 def conv_shape():
857 rng = np.random.default_rng(sb + 17)
858 W = rng.standard_normal((5, 2, 3, 3)) * 0.3
859 y = ag.conv2d(T(rng.standard_normal((2, 2, 8, 8))), T(W), bias=None, stride=1, pad=1).data
860 return y.shape == (2, 5, 8, 8), f"shape={y.shape}"
861
862 def conv_stride_shape():
863 rng = np.random.default_rng(sb + 18)
864 W = rng.standard_normal((4, 2, 3, 3)) * 0.3
865 y = ag.conv2d(T(rng.standard_normal((2, 2, 8, 8))), T(W), bias=None, stride=2, pad=1).data
866 return y.shape == (2, 4, 4, 4), f"shape={y.s
…[truncated 3233 chars]Find insertion point
grep -n "LSQ fake-quant (DOMAIN; the crux)\|def batchnorm2d\|^def fake_quant\b" submission/autograd.py | head
944:def batchnorm2d(x, gamma, beta, eps: float = 1e-5, 1001:# ============================================================ LSQ fake-quant (DOMAIN; the crux) 1002:def fake_quant(v, scale, n_levels_neg: int, n_levels_pos: int,
/app/submission/autograd.py
995 x._accum(dx) 996 997 out._backward = _bw 998 return out 999 1000 1001 # ============================================================ LSQ fake-quant (DOMAIN; the crux) 1002 def fake_quant(v, scale, n_levels_neg: int, n_levels_pos: int,
/app/submission/autograd.py
out._backward = _bw
return out
# ============================================================ LSQ fake-quant (DOMAIN; the crux)
def fake_quant(v, scale, n_levels_neg: int, n_levels_pos: int, out._backward = _bw
return out
def batchnorm1d(x, gamma, beta, eps: float = 1e-5,
running_mean=None, running_var=None, momentum: float = 0.1,
training: bool = True) -> Tensor:
"""BatchNorm over the batch axis N for a (N, C) input, per feature C. gamma,beta:(C,).
Mirrors ``batchnorm2d`` semantics (population variance for normalization, unbiased running
var update)."""
x, gamma, beta = _ensure(x), _ensure(gamma), _ensure(beta)
N, C = x.data.shape
M = N
xd = x.data
if training:
mu = xd.mean(axis=0, keepdims=True)
xc = xd - mu
var = (xc * xc).mean(axis=0, keepdims=True)
inv = 1.0 / np.sqrt(var + eps)
xhat = xc * inv
if running_mean is not None and running_var is not None:
ubvar = var * (M / _bi_max(1, M - 1))
running_mean[:] = (1 - momentum) * running_mean + momentum * mu.reshape(-1)
running_var[:] = (1 - momentum) * running_var + momentum * ubvar.reshape(-1)
else:
mu = running_mean.reshape(1, C)
var = running_var.reshape(1, C)
inv = 1.0 / np.sqrt(var + eps)
xhat = (xd - mu) * inv
g_ = gamma.data.reshape(1, C)
out = _mk(g_ * xhat + beta.data.reshape(1, C), (x, gamma, beta),
x.requires_grad or gamma.requires_grad or beta.requires_grad)
def _bw():
g = out.grad
if g is None:
return
if gamma.requires_grad:
gamma._accum(
…[truncated 619 chars]The file /app/submission/autograd.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: ag.batchnorm1d(x, gamma, beta, eps, running_mean, running_var, momentum, training)
raise NotImplementedError("BatchNorm1d.forward") return ag.batchnorm1d(x, self.gamma, self.beta, self.eps,
running_mean=self.running_mean, running_var=self.running_var,
momentum=self.momentum, training=self.training)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: wq = self.wq.quant(self.weight); return ag.conv2d(x, wq, bias=None, stride, pad=1)
raise NotImplementedError("QConv.forward") wq = self.wq.quant(self.weight)
return ag.conv2d(x, wq, bias=None, stride=self.stride, pad=1)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: h = aq(relu(bn(conv(x)))) -- in that order.
raise NotImplementedError("ConvBlock.forward")return self.aq(ag.relu(self.bn(self.conv(x))))
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: run the stem + blocks, global-average-pool, then the (2-bit) linear head.
raise NotImplementedError("QuantCNN.forward") h = X if isinstance(X, Tensor) else Tensor(X)
h = self.stem(h)
for b in self.blocks:
h = b(h)
full = h.data.shape[2]
pooled = ag.avgpool2d(h, full)
N = pooled.data.shape[0]
feat = ag.reshape(pooled, (N, self.feat))
wq = self.head_wq.quant(self.head_w)
return ag.add(ag.matmul(feat, wq), self.head_b)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: wq = self.wq.quant(self.weight); return ag.add(ag.matmul(x, wq), self.bias)
raise NotImplementedError("QLinear.forward") wq = self.wq.quant(self.weight)
return ag.add(ag.matmul(x, wq), self.bias)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: x -> reshape (N, in_dim); for each layer L: h = L["aq"](relu(L["bn"](L["fc"](h))));
# then return self.head(h).
raise NotImplementedError("QuantMLP.forward") h = X if isinstance(X, Tensor) else Tensor(X)
N = h.data.shape[0]
h = ag.reshape(h, (N, self.in_dim))
for L in self.layers:
h = L["aq"](ag.relu(L["bn"](L["fc"](h))))
return self.head(h)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.silu(x)
raise NotImplementedError("SiLU.forward")return ag.silu(x)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.elu(x, self.alpha)
raise NotImplementedError("ELU.forward")return ag.elu(x, self.alpha)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.groupnorm(x, self.gamma, self.beta, self.num_groups, self.eps)
raise NotImplementedError("GroupNorm.forward")return ag.groupnorm(x, self.gamma, self.beta, self.num_groups, self.eps)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.tanh(x@Wx + h@Wh + b)
raise NotImplementedError("RNNCell.forward")return ag.tanh(ag.add(ag.add(ag.matmul(x, self.Wx), ag.matmul(h, self.Wh)), self.b))
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: implement the GRU update with the named weights above.
raise NotImplementedError("GRUCell.forward") z = ag.sigmoid(ag.add(ag.add(ag.matmul(x, self.Wxz), ag.matmul(h, self.Whz)), self.bz))
r = ag.sigmoid(ag.add(ag.add(ag.matmul(x, self.Wxr), ag.matmul(h, self.Whr)), self.br))
n = ag.tanh(ag.add(ag.add(ag.matmul(x, self.Wxn), ag.matmul(ag.mul(r, h), self.Whn)), self.bn))
one = Tensor(np.ones_like(z.data))
return ag.add(ag.mul(ag.sub(one, z), n), ag.mul(z, h))The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: implement the LSTM update; return (h2, c2).
raise NotImplementedError("LSTMCell.forward") i = ag.sigmoid(ag.add(ag.add(ag.matmul(x, self.Wxi), ag.matmul(h, self.Whi)), self.bi))
f = ag.sigmoid(ag.add(ag.add(ag.matmul(x, self.Wxf), ag.matmul(h, self.Whf)), self.bf))
g = ag.tanh(ag.add(ag.add(ag.matmul(x, self.Wxg), ag.matmul(h, self.Whg)), self.bg))
o = ag.sigmoid(ag.add(ag.add(ag.matmul(x, self.Wxo), ag.matmul(h, self.Who)), self.bo))
c2 = ag.add(ag.mul(f, c), ag.mul(i, g))
h2 = ag.mul(o, ag.tanh(c2))
return h2, c2The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.fake_quant_per_channel(w, self.scale, self.neg, self.pos, axis=0)
raise NotImplementedError("PerChannelWeightQuant.quant")return ag.fake_quant_per_channel(w, self.scale, self.neg, self.pos, axis=0)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.fake_quant_affine(x, self.scale, self.zero_point, self.neg, self.pos)
raise NotImplementedError("AffineActQuant.forward")return ag.fake_quant_affine(x, self.scale, self.zero_point, self.neg, self.pos)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.rms_norm(x, self.gamma, self.eps)
raise NotImplementedError("RMSNorm.forward")return ag.rms_norm(x, self.gamma, self.eps)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.instance_norm(x, self.gamma, self.beta, self.eps)
raise NotImplementedError("InstanceNorm2d.forward")return ag.instance_norm(x, self.gamma, self.beta, self.eps)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.embedding(self.weight, idx)
raise NotImplementedError("Embedding.forward")return ag.embedding(self.weight, idx)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.conv_transpose2d(x, self.weight, bias=self.bias, stride=self.stride, pad=self.padding)
raise NotImplementedError("ConvTranspose2d.forward")return ag.conv_transpose2d(x, self.weight, bias=self.bias, stride=self.stride, pad=self.padding)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.conv2d_gen(x, self.weight, bias=self.bias, stride=self.stride,
# pad=self.padding, dilation=self.dilation, groups=1)
raise NotImplementedError("DilatedConv2d.forward") return ag.conv2d_gen(x, self.weight, bias=self.bias, stride=self.stride,
pad=self.padding, dilation=self.dilation, groups=1)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: return ag.fake_quant_lsq_plus(x, self.scale, self.beta, self.neg, self.pos)
raise NotImplementedError("LSQPlusActQuant.forward")return ag.fake_quant_lsq_plus(x, self.scale, self.beta, self.neg, self.pos)
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: depthwise conv2d_gen(groups=Cin) on the LSQ-quantized dw_weight, then pointwise
# conv2d_gen(groups=1) on the LSQ-quantized pw_weight.
raise NotImplementedError("QDWSepConv.forward") dwq = self.dw_wq.quant(self.dw_weight)
h = ag.conv2d_gen(x, dwq, bias=None, stride=self.stride, pad=1, dilation=1, groups=self.Cin)
pwq = self.pw_wq.quant(self.pw_weight)
return ag.conv2d_gen(h, pwq, bias=None, stride=1, pad=0, dilation=1, groups=1)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: conv -> bn -> relu -> aq
raise NotImplementedError("QSepBlock.forward")return self.aq(ag.relu(self.bn(self.conv(x))))
The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
/app/submission/nn.py
# TODO: stem -> blocks -> avgpool2d(full window) -> reshape (N,C) -> matmul(LSQ head) + bias
raise NotImplementedError("QuantSepCNN.forward") h = X if isinstance(X, Tensor) else Tensor(X)
h = self.stem(h)
for b in self.blocks:
h = b(h)
full = h.data.shape[2]
pooled = ag.avgpool2d(h, full)
N = pooled.data.shape[0]
feat = ag.reshape(pooled, (N, self.feat))
wq = self.head_wq.quant(self.head_w)
return ag.add(ag.matmul(feat, wq), self.head_b)The file /app/submission/nn.py has been updated successfully. (file state is current in your context , no need to Read it back)
Check remaining stubs
grep -rn "NotImplementedError\|raise NotImpl" submission/nn.py submission/optim.py submission/data.py | grep -v "def named_params"
submission/nn.py:39: raise NotImplementedError
Run all public checks (summary)
python3 run_checks.py --quiet 2>&1 | tail -20
------------------------------------------------------------------------ autograd_grads 115/115 | quant_grads 21/21 | nn_forward 53/53 | optim 25/25 | integration 6/6 | data 2/2 TOTAL 222/222 public checks passing All public checks pass. Now train qat_model.npz to clear the held-out top-1 threshold (the grader re-checks components with DIFFERENT seeds).
Inspect dataset
python3 -c "
import numpy as np
d=np.load('data/train.npz')
print({k:(v.shape,v.dtype) for k,v in d.items()})
X,y=d['X'],d['y']
print('classes',np.unique(y),'counts',np.bincount(y))
print('X range',X.min(),X.max())
"{'X': ((2500, 3, 16, 16), dtype('uint8')), 'y': ((2500,), dtype('int64'))}
classes [0 1 2 3 4 5 6 7 8 9] counts [250 250 250 250 250 250 250 250 250 250]
X range 0 255/app/submission/train.py
def train(data_path, out_path, epochs=30, seed=0, n_classes=10):
# TODO: load + normalize the data; build QuantCNN(n_classes, WIDTHS, seed); initialize the LSQ
# step sizes; build the optimizer with weight decay only on the conv/head weights; run the QAT
# loop (forward -> cross_entropy -> backward -> clip_grad_norm -> step) with an LR schedule;
# keep your best epoch; BAKE the quantized weights; save the state_dict to out_path.
raise NotImplementedError("implement the QAT training loop")def _init_lsq_scales(model):
nps = model.named_params()
for nm, p in nps.items():
if nm.endswith("wq.scale"):
wkey = nm[:-len("wq.scale")] + "weight"
w = nps[wkey].data
p.data[...] = max(2.0 * float(np.mean(np.abs(w))) / np.sqrt(1.0), 1e-2)
elif nm.endswith("aq.scale"):
p.data[...] = 1.0
def _accuracy(model, Xn, y, bs=256):
model.set_training(False)
correct = 0
for s in range(0, Xn.shape[0], bs):
xb = Xn[s:s + bs]
logits = model(xb).data
correct += int((logits.argmax(axis=1) == y[s:s + bs]).sum())
return correct / Xn.shape[0]
def _bake(model):
from nn import W_NEG, W_POS
nps = model.named_params()
for nm, p in nps.items():
if nm.endswith(".weight") and ("conv" in nm or "head" in nm or "stem" in nm or "blocks" in nm):
skey = nm[:-len("weight")] + "wq.scale"
if skey in nps:
s = float(nps[skey].data.reshape(()))
s = s if abs(s) > 1e-12 else 1e-12
p.data[...] = np.round(np.clip(p.data / s, -W_NEG, W_POS)) * s
def train(data_path, out_path, epochs=60, seed=0, n_classes=10):
rng = np.random.default_rng(seed)
X, y = D.load_npz(data_path)
Xn = D.normalize(X)
# internal train/val split for best-epoch selection
perm = np.random.default_rng(1234).permutation(Xn.shape[0])
n_val = max(1, int(0.12 * Xn.shape[0]))
val_idx, tr_idx = perm[:n_val], perm[n_val
…[truncated 1777 chars]The file /app/submission/train.py has been updated successfully. (file state is current in your context , no need to Read it back)
Quick 3-epoch smoke training
cd submission && timeout 300 python3 train.py --epochs 3 --out /tmp/test_model.npz 2>&1 | tail -10
No file changes, the agent left the workspace untouched.
=== SyncVals verifier (local re-grade of the agent's own checkpoint) === COMPONENT CONFORMANCE SUITE: 278/278 cases passed (all milestones pass: True) FINAL METRIC: held-out INT2 top-1 = 0.8807 >= threshold 0.7 REWARD = 1 (1 iff every component milestone passes AND the sealed held-out metric clears its threshold) NOTE: the in-sandbox training in the 481MB e2b box was OOM-killed (0-byte checkpoint), so the raw in-sandbox reward was an infrastructure artifact. This reward is from a faithful LOCAL re-train of the agent's OWN train.py (24GB, no OOM) with its own default hyperparameters, then re-graded by the real verifier.
Reproduce this trial: git checkout 2f94510 && PYTHONPATH=src python3 scripts/build_site.py , then open trial/trial_5636544da98d4408. Re-running the agent live requires EVAL_PLATFORM_ENABLE_OAUTH_SMOKE=1 and is non-deterministic.
Trial trial_5636544da98d4408 · verifier authoritative; classifier explanatory.