SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.08066 · 2019

Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 8 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1903.08066.json · badge: /api/ran/1903.08066.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PannenetsF/TQT community (classifier label)
classifier basis not recorded on the link
2 ran · 8 no recorded run
FunctionStatusWhere it lives
kl_divergence Ran
ran on a synthesized input
PannenetsF/TQT/tqt/analyse/kl.py
code served (permissive licence) · get_code("ed42e29f9cacc3f3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# kl_divergence computes (ha * (ha / hb).log()).sum()
# It expects:
# - ha: a tensor that supports division, log, and sum operations
# - hb: a tensor that supports division (denominator)
# Both should be broadcastable and support element-wise operations

ha = torch.tensor([0.1, 0.2, 0.3, 0.4], dtype=torch.float32)
hb = torch.tensor([0.15, 0.25, 0.35, 0.25], dtype=torch.float32)

ARGS = {
    "ha": ha,
    "hb": hb,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_bn_fold_with_previous Ran
ran on a synthesized input
PannenetsF/TQT/tqt/utils.py
code served (permissive licence) · get_code("99cb38faf7eee70f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple network with BatchNorm2d
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 4, kernel_size=3)
        self.bn1 = nn.BatchNorm2d(4)
        self.conv2 = nn.Conv2d(4, 8, kernel_size=3)
        self.bn2 = nn.BatchNorm2d(8)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.conv2(x)
        x = self.bn2(x)
        return x

# Create network instance
net = SimpleNet()

# Create a Conv2d module to act as pre_proc (the function calls pre_proc.fold() if net_proc is BatchNorm2d)
pre_conv = nn.Conv2d(3, 4, kernel_size=3)

# Add a fold method to the Conv2d so it can be called (mimic the expected interface)
def mock_fold(self, bn_module):
    pass

pre_conv.fold = lambda bn_module: mock_fold(pre_conv, bn_module)

ARGS = {
    'net_proc': net,
    'name': 'net',
    'pre_proc': pre_conv,
    'pre_name': 'pre_conv',
    'show': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
config_acti Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/config.py
code served (permissive licence) · get_code("88f6fe05aa7308db")
How it ran

no invocation recorded.

config_bn Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/config.py
code served (permissive licence) · get_code("cb7a1e0dbb7a09a9")
How it ran

no invocation recorded.

config_conv_linear Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/config.py
code served (permissive licence) · get_code("f2f3595832793e27")
How it ran

no invocation recorded.

fold_CB Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/fold/fold_op.py
code served (permissive licence) · get_code("94a45a0faabc1f13")
How it ran

no invocation recorded.

fold_CBR Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/fold/fold_op.py
code served (permissive licence) · get_code("239de305c96f91ce")
How it ran

no invocation recorded.

fold_SABR Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/fold/fold_op.py
code served (permissive licence) · get_code("f2c965afd1753bc3")
How it ran

no invocation recorded.

get_all_layers Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/fused_config.py
code served (permissive licence) · get_code("4fea127b33348b00")
How it ran

no invocation recorded.

kl_similarity Not yet run
unverified (harvested, no recorded run)
PannenetsF/TQT/tqt/analyse/kl.py
code served (permissive licence) · get_code("a0e0d8bfa694710c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a method of training quantization thresholds (TQT) for uniform symmetric quantizers using standard backpropagation and gradient descent. Contrary to prior work, we show that a careful analysis of the straight-through estimator for threshold gradients allows for a natural range-precision trade-off leading to better optima. Our quantizers are constrained to use power-of-2 scale-factors and per-tensor scaling of weights and activations to make it amenable for hardware implementations. We present analytical support for the general robustness of our methods and empirically validate them on various CNNs for ImageNet classification. We are able to achieve near-floating-point accuracy on traditionally difficult networks such as MobileNets with less than 5 epochs of quantized (8-bit) retraining. Finally, we present Graffitist, a framework that enables automatic quantization of TensorFlow graphs for TQT (available at https://github.com/Xilinx/graffitist ).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1903.08066")
get_code_for_paper("1903.08066")
have("1903.08066")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1903.08066.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1903.08066.svg)](https://syntology.ai/paper/1903.08066)

Connect an agent — have() is free.