SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.00992 · 2020

Rethinking Channel Dimensions for Efficient Model Design

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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, 1 violated it and 6 have no contract verdict; 0 failures of our instrument; 1 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/2007.00992.json · badge: /api/ran/2007.00992.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
lyqcom/rexnet canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
paperswithcode/model-index community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
ysbsb/ReXNet-PyTorch community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
ysbsb/ReXNet-PyTorch/utils.py
code served (permissive licence) · get_code("f84cc119467969e4")
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 list, ndim 2, 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

torch.manual_seed(0)

# Create output tensor: batch_size=2, num_classes=4
# This represents logits/scores for each class
output = torch.randn(2, 4)

# Create target tensor: batch_size=2
# Each element is a class index (0-3)
target = torch.tensor([1, 3])

# topk parameter: tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk
}
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 list, ndim 2, dtype family float — a list 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
full_filepath Ran
ran on a synthesized input
paperswithcode/model-index/modelindex/utils.py
code served (permissive licence) · get_code("14cb906d9717c748")
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 str. The image it ran in was not recorded. If your copy returns the same type 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 os

def full_filepath(path: str, cur_filepath: str=None):
    """Return the full file path based on a possibly relative path (path)
    and the current file path (cur_filepath)
    """
    if cur_filepath is not None:
        dirname = os.path.dirname(cur_filepath)
        if dirname:
            path = os.path.join(dirname, path)
    return path


ARGS = {
    "path": "myfile.txt",
    "cur_filepath": "/home/user/project/config.py"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
has_at_least_one_models_key Ran
ran on a synthesized input
paperswithcode/model-index/modelindex/load_model_index.py
code served (permissive licence) · get_code("141717f5e0516401")
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 bool, 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.

# Analyze the function
# has_at_least_one_models_key takes lc_keys parameter
# It checks if there's intersection between model_keys set and set(lc_keys)
# lc_keys should be an iterable of strings (lowercase keys)

# Test case 1: lc_keys with at least one model key
ARGS = {
    "lc_keys": ['paper', 'other_key', 'something']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
load_ckpt Ran
ran on a synthesized input
ysbsb/ReXNet-PyTorch/utils.py
code served (permissive licence) · get_code("0535326f88e06187")
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
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory for saving checkpoint
temp_dir = tempfile.mkdtemp()
savepath = temp_dir + '/'

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a checkpoint with the required structure
checkpoint = {
    'state_dict': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'epoch': 5
}

# Save the checkpoint
checkpoint_fpath = savepath + 'model_weight_latest.pth'
torch.save(checkpoint, checkpoint_fpath)

# Create args object with savepath attribute
class Args:
    def __init__(self, savepath):
        self.savepath = savepath

args = Args(savepath)

# Create fresh model and optimizer instances for loading
model_fresh = SimpleModel()
optimizer_fresh = torch.optim.SGD(model_fresh.parameters(), lr=0.01)

ARGS = {
    'model': model_fresh,
    'optimizer': optimizer_fresh,
    'args': args
}
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
load_raw_from_markdown Ran
ran on a synthesized input
paperswithcode/model-index/modelindex/utils.py
code served (permissive licence) · get_code("2698f6291a00ce3f")
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 list, 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 tempfile
import os

# Create a temporary markdown file with YAML frontmatter containing model-index
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.md")

# Write a markdown file with YAML frontmatter
markdown_content = """---
model-index:
- name: test-model
  results:
    - task: image-classification
      dataset: imagenet
---

# Test Model

This is a test markdown file with model metadata.
"""

with open(temp_file, 'w') as f:
    f.write(markdown_content)

ARGS = {
    "path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
markdown, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
lowercase_keys Ran
ran on a synthesized input
paperswithcode/model-index/modelindex/utils.py
code served (permissive licence) · get_code("26892faf1ee64a87")
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 dict. The image it ran in was not recorded. If your copy returns the same type 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

def lowercase_keys(d: dict):
    """Map keys to lowercase, e.g. it will map a dict with a MODELS key into
    {"models": "MODELS"}. This allows for a unified way of naming custom-case keys.
    """
    out = {}
    for k in d.keys():
        out[k.lower()] = k
    return out

ARGS = {
    "d": {
        "MODELS": "model_config",
        "DATA": [1, 2, 3],
        "LEARNING_RATE": 0.001,
        "Batch_Size": 32
    }
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
str2bool Ran
ran, violated the contract we drafted
lyqcom/rexnet/config.py
code served (permissive licence) · get_code("17061f7e01a6fc86")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned bool, 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 argparse

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', '1'):
        return True
    elif v.lower() in ('no', 'false', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Test with a string that should return True
ARGS = {'v': 'true'}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
rand_bbox Not yet run
unverified (harvested, no recorded run)
ysbsb/ReXNet-PyTorch/train_sgd_randaugv1_cutmix.py
pointer only (licence: MIT); the stored copy get_code serves, from deeplearning-wisc/dream-ood, is pointer only (licence: NOASSERTION) · get_code("d34a085d71b8f4b5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from deeplearning-wisc/dream-ood, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 6 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.

FunctionAlso present inEarliest-datedOthers named
rand_bbox 13 other papers
3 dated earlier, 10 later
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
2002.11102 (2020-02)
On Feature Normalization and Data Augmentation
2003.05438 (2020-03)
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning
and 10 more not named here
str2bool 2 other papers
2 later
2104.01136 (2021-04)
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
2206.10589 (2022-06)
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications

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

Designing an efficient model within the limited computational cost is challenging. We argue the accuracy of a lightweight model has been further limited by the design convention: a stage-wise configuration of the channel dimensions, which looks like a piecewise linear function of the network stage. In this paper, we study an effective channel dimension configuration towards better performance than the convention. To this end, we empirically study how to design a single layer properly by analyzing the rank of the output feature. We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction. Based on the investigation, we propose a simple yet effective channel configuration that can be parameterized by the layer index. As a result, our proposed model following the channel parameterization achieves remarkable performance on ImageNet classification and transfer learning tasks including COCO object detection, COCO instance segmentation, and fine-grained classifications. Code and ImageNet pretrained models are available at https://github.com/clovaai/rexnet.

For agents

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

get_harvested_code_for_paper("2007.00992")
get_code_for_paper("2007.00992")
have("2007.00992")

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

curl https://syntology.ai/api/ran/2007.00992.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.00992.svg)](https://syntology.ai/paper/2007.00992)

Connect an agent — have() is free.