SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1703.06211 · 2017

Deformable Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/1703.06211.json · badge: /api/ran/1703.06211.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
oeway/pytorch-deform-conv reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
tianhai123/deform-conv community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
necla-ml/Deformable-ConvNets-py3 community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
metaphorz/deep-image-prior-hqskipnet extension (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_rcnn_names Ran
ran on a synthesized input
necla-ml/Deformable-ConvNets-py3/faster_rcnn/core/metric.py
pointer only (licence: MIT); the stored copy get_code serves, from msracver/Flow-Guided-Feature-Aggregation, is pointer only (licence: MIT) · get_code("bbf8005ce03c08cf")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, necla-ml/Deformable-ConvNets-py3, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. A run is recorded.

np_repeat_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oeway/pytorch-deform-conv/torch_deform_conv/deform_conv.py
code served (permissive licence) · get_code("99464264d818eda2")
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 ndarray, ndim 3, dtype family int, shape (5, 3, 4) 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 numpy as np

# Create a 2D numpy array with distinct dimensions
a = np.array([[1, 2, 3, 4],
              [5, 6, 7, 8],
              [9, 10, 11, 12]])  # Shape: (3, 4)

# Number of times to repeat
repeats = 5

ARGS = {
    'a': a,
    'repeats': repeats
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (5, 3, 4) — shape (5, 3, 4) 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
tf_repeat Ran
ran on a synthesized input
tianhai123/deform-conv/deform_conv/deform_conv.py
code served (permissive licence) · get_code("8a0d90e615ac2db1")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create a small 1D tensor for testing
a_value = tf.constant([1.0, 2.0, 3.0, 4.0], dtype=tf.float32)

# Define the repeats parameter
repeats_value = 3

# Define the axis parameter (default is 0, but we'll be explicit)
axis_value = 0

# Construct the ARGS dictionary with all parameters
ARGS = {
    'a': a_value,
    'repeats': repeats_value,
    'axis': axis_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float — no output shape is stated: observe_signature.py recorded SymbolicTensor ndim 1, which disagrees with the fixture run
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
tf_repeat_2d Ran
ran on a synthesized input
tianhai123/deform-conv/deform_conv/deform_conv.py
code served (permissive licence) · get_code("89bffcebf8e96f1f")
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 EagerTensor, ndim 3, dtype family float, shape (2, 4, 3) 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 tensorflow as tf
import numpy as np

# Create a small 2D tensor (4 rows, 3 columns)
a = tf.constant([[1.0, 2.0, 3.0],
                 [4.0, 5.0, 6.0],
                 [7.0, 8.0, 9.0],
                 [10.0, 11.0, 12.0]], dtype=tf.float32)

# Number of times to repeat the 2D tensor along a new first dimension
repeats = 2

ARGS = {
    "a": a,
    "repeats": repeats
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
th_flatten Ran
ran, honoured the contract we drafted
oeway/pytorch-deform-conv/torch_deform_conv/deform_conv.py
code served (permissive licence) · get_code("0ce99b2d4c408918")
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 Tensor, ndim 1, dtype family float, shape (24,) 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

torch.manual_seed(0)

# Create a small tensor with distinct dimensions
# Using shape (2, 3, 4) to have distinct dimensions
a = torch.randn(2, 3, 4)

ARGS = {
    'a': a
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (24,) — shape (24,) 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
th_repeat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oeway/pytorch-deform-conv/torch_deform_conv/deform_conv.py
code served (permissive licence) · get_code("7d15625ab429830a")
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 Tensor, ndim 1, dtype family float, shape (15,) 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

torch.manual_seed(0)

# Create a 1D tensor as required by the function
a = torch.tensor([1.0, 2.0, 3.0, 4.0, 5.0])

# Number of times to repeat each element
repeats = 3

# Axis parameter (default is 0, and function is designed for 1D tensors)
axis = 0

ARGS = {
    'a': a,
    'repeats': repeats,
    'axis': axis
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (15,) — shape (15,) 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
convert_context Not yet run
unverified (harvested, no recorded run)
necla-ml/Deformable-ConvNets-py3/dcn/utils/load_model.py
pointer only (licence: MIT) · get_code("85b0d97b5f005697")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, necla-ml/Deformable-ConvNets-py3, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

skip Not yet run
unverified (harvested, no recorded run)
metaphorz/deep-image-prior-hqskipnet/models/skip.py
pointer only (licence: NOASSERTION) · get_code("2d0d83b79a1d4a05")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, metaphorz/deep-image-prior-hqskipnet (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.

tf_flatten Not yet run
unverified (harvested, no recorded run)
tianhai123/deform-conv/deform_conv/deform_conv.py
pointer only (licence: MIT); the stored copy get_code serves, from JunweiLiang/social-distancing-prediction, is pointer only (licence: Apache-2.0) · get_code("12e6fdbf5080bbb4")
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 JunweiLiang/social-distancing-prediction, and Apache-2.0, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 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
get_rcnn_names 4 other papers
1 dated earlier, 1 the same month, 2 later
1611.07715 (2016-11)
Deep Feature Flow for Video Recognition
1703.10025 (2017-03)
Flow-Guided Feature Aggregation for Video Object Detection
1803.06799 (2018-03)
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN
and 1 more not named here
convert_context 1 other paper
1 the same month
1703.06870 (2017-03)
Mask R-CNN
tf_flatten 1 other paper
1 later
1902.03748 (2019-02)
Peeking into the Future: Predicting Future Person Activities and Locations in Videos

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 2026-11-22.

Repositories linked to this paper

More are linked than shown here.

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

Abstract

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from target tasks, without additional supervision. The new modules can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard back-propagation, giving rise to deformable convolutional networks. Extensive experiments validate the effectiveness of our approach on sophisticated vision tasks of object detection and semantic segmentation. The code would be released.

For agents

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

get_harvested_code_for_paper("1703.06211")
get_code_for_paper("1703.06211")
have("1703.06211")

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

curl https://syntology.ai/api/ran/1703.06211.json

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

[![Syntology run record](https://syntology.ai/api/ran/1703.06211.svg)](https://syntology.ai/paper/1703.06211)

Connect an agent — have() is free.