SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.05049 · 2019

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

arXiv · PDF · Open in the Atlas

Code that ran

24 of 34 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 10 have no contract verdict; 13 failures of our instrument; 10 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/1904.05049.json · badge: /api/ran/1904.05049.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
lxtGH/OctaveConv_pytorch reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
markliou/OctConv community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
xu3kev/octconv-chainer community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
kk1694/octaveconv-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
matsuren/OctaveConv.pytorch reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
renmada/OctConv-paddle community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
braincreators/octconv community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
Manuscrit/OctaveConv_PlugAndPlay reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
d-li14/octconv.pytorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 4 no recorded run
deeplearningforfun/OctConv community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
zrl4836/tensorflow_octConv reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
OctConv_block Ran
ran on a synthesized input
markliou/OctConv/OctConv_cifar10.py
code served (permissive licence) · get_code("e241a3df023ced79")
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. 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 tensorflow as tf

# Create small input tensors for Hx and Lx
# Hx: high-frequency input, shape (batch=2, height=4, width=4, channels=3)
# Lx: low-frequency input, shape (batch=2, height=2, width=2, channels=3)
Hx = tf.random.normal((2, 4, 4, 3))
Lx = tf.random.normal((2, 2, 2, 3))

# Define parameters
alpha_val = 0.8
channel_no = 8
kernel_size = 3
activation_fn = tf.nn.relu

ARGS = {
    'Hx': Hx,
    'Lx': Lx,
    'alpha': alpha_val,
    'channel_no': channel_no,
    'kernel_size': kernel_size,
    'activation': activation_fn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
OctConv_final Ran
ran on a synthesized input
markliou/OctConv/OctConv_cifar10.py
code served (permissive licence) · get_code("44c563b1e8c05156")
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 4, dtype family float, shape (2, 4, 4, 8) 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 small input tensors
# Hx: high-frequency input, shape (batch=2, height=4, width=4, channels=3)
Hx = tf.constant(np.random.randn(2, 4, 4, 3).astype(np.float32))

# Lx: low-frequency input, shape (batch=2, height=2, width=2, channels=3)
# Lower spatial resolution to simulate octave structure
Lx = tf.constant(np.random.randn(2, 2, 2, 3).astype(np.float32))

# Number of output channels
channel_no = 8

# Kernel size for convolutions
kernel_size = 3

# Activation function
activation = tf.nn.relu

ARGS = {
    'Hx': Hx,
    'Lx': Lx,
    'channel_no': channel_no,
    'kernel_size': kernel_size,
    'activation': activation
}
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 4, dtype family float, shape (2, 4, 4, 8) — shape (2, 4, 4, 8) 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
OctConv_ini Ran
ran on a synthesized input
markliou/OctConv/OctConv_cifar10.py
code served (permissive licence) · get_code("9b878790d728c6b8")
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. 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)
np.random.seed(0)

# Create a small input tensor: batch=2, height=4, width=3, channels=1
x = tf.random.normal((2, 4, 3, 1), dtype=tf.float32)

# Define alpha parameter
alpha = 0.8

# Define channel_no
channel_no = 10

# Define kernel_size
kernel_size = 3

# Define activation function
activation = tf.nn.relu

# Construct ARGS dictionary with all parameters
ARGS = {
    'x': x,
    'alpha': alpha,
    'channel_no': channel_no,
    'kernel_size': kernel_size,
    'activation': activation
}
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 tuple — a tuple output has no array shape of its own; none is 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
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
braincreators/octconv/benchmarks/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from toytiny/milliflow, is pointer only (licence: NOASSERTION) · get_code("4134b8420b4c48b5")
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 toytiny/milliflow, 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. A run is recorded.

check_status Ran
ran on a synthesized input
deeplearningforfun/OctConv/octconv_basic/frequency_separated_layer.py
code served (permissive licence) · get_code("d8a2457d32979202")
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 numpy as np

torch.manual_seed(0)

ARGS = {
    "alpha_in": 0.5,
    "alpha_out": 0.3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
lxtGH/OctaveConv_pytorch/libs/nn/OCtaveResnet.py
code served (permissive licence) · get_code("08458eb1eaf76e36")
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 Conv2d. 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
import torch.nn as nn

torch.manual_seed(0)

# The function conv1x1 takes in_planes, out_planes, and stride
# in_planes: number of input channels
# out_planes: number of output channels
# stride: stride for the convolution

in_planes = 8
out_planes = 16
stride = 2

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes,
    'stride': stride
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv1x1_octave Ran
ran; our contract draft was wrong, not the code
Manuscrit/OctaveConv_PlugAndPlay/plug_and_play.py
pointer only (licence: NONE) · get_code("123e785ddb5335b8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Manuscrit/OctaveConv_PlugAndPlay when it was checked. 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
lxtGH/OctaveConv_pytorch/libs/nn/OCtaveResnet.py
code served (permissive licence) · get_code("e5535c2973c06adf")
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 Conv2d. 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
import torch.nn as nn

torch.manual_seed(0)

# conv3x3 parameters:
# - in_planes: number of input channels (int)
# - out_planes: number of output channels (int)
# - stride: stride for convolution (int, default=1)
# - groups: number of groups for grouped convolution (int, default=1)

ARGS = {
    'in_planes': 8,
    'out_planes': 16,
    'stride': 2,
    'groups': 2
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3_octave Ran
ran; our contract draft was wrong, not the code
Manuscrit/OctaveConv_PlugAndPlay/plug_and_play.py
pointer only (licence: NONE) · get_code("a0857154e91e28f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Manuscrit/OctaveConv_PlugAndPlay when it was checked. 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.

conv_bn Ran
ran; our contract draft was wrong, not the code
d-li14/octconv.pytorch/oct_mobilenet.py
code served (permissive licence) · get_code("2f7853ff01cbbc29")
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 Sequential. 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

torch.manual_seed(0)

inp = 3
oup = 8
stride = 2

ARGS = {
    'inp': inp,
    'oup': oup,
    'stride': stride
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
fast_collate Ran
ran; our contract draft was wrong, not the code
lxtGH/OctaveConv_pytorch/main_imagenet.py
code served (permissive licence) · get_code("0ae841d977200ffa")
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 tuple. 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
import numpy as np
from PIL import Image

torch.manual_seed(0)

# Create mock PIL Images with targets
# The function expects batch to be a list of tuples (img, target)
# where img is a PIL Image and target is an integer label

# Create small PIL Images (width=5, height=4, RGB)
img1 = Image.new('RGB', (5, 4), color=(255, 0, 0))
img2 = Image.new('RGB', (5, 4), color=(0, 255, 0))

# Create batch as list of (image, target) tuples
batch = [
    (img1, 0),
    (img2, 1)
]

ARGS = {
    'batch': batch
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
flush_print Ran
ran; our contract draft was wrong, not the code
lxtGH/OctaveConv_pytorch/main_imagenet.py
code served (permissive licence) · get_code("f4c0610b55fcb289")
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 function. 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 sys

def example_print_function(*args, **kwargs):
    """A simple print function that can be wrapped"""
    print(*args, **kwargs)

ARGS = {
    'func': example_print_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
get_num_channel Ran
ran on a synthesized input
xu3kev/octconv-chainer/octconv.py
code served (permissive licence) · get_code("c747d9a6671d56d9")
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 int; 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)

# The function takes two parameters: channels (a number) and alpha (a number)
# It performs arithmetic operations on them to compute channel dimensions

ARGS = {
    "channels": 64,
    "alpha": 0.5,
}
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 int — 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
noop Ran
ran, honoured the contract we drafted
kk1694/octaveconv-pytorch/octxresnet.py
pointer only (licence: NONE) · get_code("e08d9496019166da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kk1694/octaveconv-pytorch when it was checked. 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.

norm_conv1x1 Ran
ran; our contract draft was wrong, not the code
matsuren/OctaveConv.pytorch/models/octave_resnet.py
code served (permissive licence) · get_code("739a2595c710af6b")
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 Conv2d. 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
import torch.nn as nn

torch.manual_seed(0)

# The function creates a 1x1 convolution layer
# Parameters:
# - in_planes: number of input channels
# - out_planes: number of output channels
# - stride: stride for the convolution (default 1)
# - type: not used in the function body, can be None or any value

in_planes = 3
out_planes = 8
stride = 2
type_param = None

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes,
    'stride': stride,
    'type': type_param
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
norm_conv3x3 Ran
ran; our contract draft was wrong, not the code
matsuren/OctaveConv.pytorch/models/octave_resnet.py
code served (permissive licence) · get_code("4a8c216d40baf37b")
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 Conv2d. 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
import torch.nn as nn

torch.manual_seed(0)

# The function takes in_planes, out_planes, stride, and type as parameters
# in_planes and out_planes are integers representing number of channels
# stride is an integer (default 1)
# type is optional and not used in the function body (default None)

ARGS = {
    'in_planes': 3,
    'out_planes': 16,
    'stride': 1,
    'type': None
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
oct_add Ran
ran on a synthesized input
xu3kev/octconv-chainer/octconv.py
code served (permissive licence) · get_code("b2719846a9cc00e2")
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 2, dtype family float, shape (2, 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 torch
import numpy as np

torch.manual_seed(0)

# The function oct_add handles:
# - Two tuples: adds element-wise
# - One tuple, one non-tuple: adds non-tuple to first element of tuple
# - Two non-tuples: standard addition

# Create test arguments that exercise the function
x1 = torch.tensor([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]])  # 2x4 tensor
x2 = torch.tensor([[0.5, 1.5, 2.5, 3.5], [4.5, 5.5, 6.5, 7.5]])  # 2x4 tensor

ARGS = {
    "x1": x1,
    "x2": x2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
oct_conv3x3 Ran
ran; our contract draft was wrong, not the code
matsuren/OctaveConv.pytorch/models/octave_resnet.py
code served (permissive licence) · get_code("2960ed915c2fe837")
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 OctConv. 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
import torch.nn as nn

torch.manual_seed(0)

# The oct_conv3x3 function creates an OctConv module
# Parameters: in_planes, out_planes, stride=1, type='normal'

# We need to provide valid integer values for in_planes and out_planes
# stride can be 1 or 2
# type can be 'first', 'last', or 'normal'

ARGS = {
    'in_planes': 16,
    'out_planes': 32,
    'stride': 1,
    'type': 'normal'
}
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 OctConv — a OctConv output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OctConv 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
oct_function Ran
ran on a synthesized input
xu3kev/octconv-chainer/octconv.py
code served (permissive licence) · get_code("244dd0289c2757ea")
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 function. 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
import torch.nn as nn

torch.manual_seed(0)

# The function oct_function takes a single parameter 'f' which should be a callable
# that can process individual values or tuples of values.
# Looking at the function body, f is called with individual arguments like f(x[0]) and f(x[1])

# Create a simple callable function that processes tensors or scalars
def simple_function(x):
    """A simple function that can handle tensors or scalars"""
    if isinstance(x, torch.Tensor):
        return x * 2
    else:
        return x * 2 if x is not None else None

ARGS = {
    "f": simple_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
rerange_index Ran
ran on a synthesized input
renmada/OctConv-paddle/ppcls/loss/comfunc.py
code served (permissive licence) · get_code("21421188135068e9")
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 ndarray, ndim 1, dtype family int, shape (16,) 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

ARGS = {
    "batch_size": 4,
    "samples_each_class": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 1, dtype family int, shape (16,) — shape (16,) 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
setup_logger Ran
ran on a synthesized input
braincreators/octconv/benchmarks/utils.py
code served (permissive licence) · get_code("89ee486ad2a5cc66")
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 Logger. 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 logging
import os
import sys
import tempfile

# Create a temporary directory for logging
temp_dir = tempfile.mkdtemp()

ARGS = {
    'name': 'test_logger',
    'save_dir': temp_dir,
    'distributed_rank': 0,
    'filename': 'log.txt'
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
similar_architectures Ran
ran on a synthesized input
renmada/OctConv-paddle/paddleclas.py
code served (permissive licence) · get_code("f262aa35d9f2b50f")
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 torch
import numpy as np
from difflib import SequenceMatcher

torch.manual_seed(0)

ARGS = {
    'name': 'resnet',
    'names': [
        'resnet50',
        'resnet101',
        'vgg16',
        '__internal_model',
        'inception_v3',
        'mobilenet_v2',
        'densenet121',
        'efficientnet_b0',
        'squeezenet1_0',
        'shufflenet_v2'
    ],
    'thresh': 0.1,
    'topk': 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
tuplify Ran
ran; our contract draft was wrong, not the code
kk1694/octaveconv-pytorch/octconv.py
pointer only (licence: NONE) · get_code("fb0e7024c16a4e85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kk1694/octaveconv-pytorch when it was checked. 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.

tuplify_bn Ran
ran; our contract draft was wrong, not the code
kk1694/octaveconv-pytorch/octconv.py
pointer only (licence: NONE) · get_code("bceb811dd9e9945c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, kk1694/octaveconv-pytorch when it was checked. 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.

OctConv Not yet run
unverified (harvested, no recorded run)
zrl4836/tensorflow_octConv/tf_octConv.py
pointer only (licence: NONE) · get_code("14a2c31b31f88653")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zrl4836/tensorflow_octConv when it was checked. 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.

Octresnet50 Not yet run
unverified (harvested, no recorded run)
lxtGH/OctaveConv_pytorch/libs/nn/OCtaveResnet.py
code served (permissive licence) · get_code("7e7c76ac270493de")
How it ran

no invocation recorded.

check_model_file Not yet run
unverified (harvested, no recorded run)
renmada/OctConv-paddle/paddleclas.py
code served (permissive licence) · get_code("a39394c9a8e29425")
How it ran

no invocation recorded.

conv_dw Not yet run
unverified (harvested, no recorded run)
d-li14/octconv.pytorch/oct_mobilenet.py
code served (permissive licence) · get_code("fe50a22175e3702c")
How it ran

no invocation recorded.

conv_net Not yet run
unverified (harvested, no recorded run)
markliou/OctConv/VanillaConv_cifar10.py
code served (permissive licence) · get_code("112117a703e03d5c")
How it ran

no invocation recorded.

firstOctConv Not yet run
unverified (harvested, no recorded run)
zrl4836/tensorflow_octConv/tf_octConv.py
pointer only (licence: NONE) · get_code("295549ea9af0b7a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zrl4836/tensorflow_octConv when it was checked. 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.

lastOctConv Not yet run
unverified (harvested, no recorded run)
zrl4836/tensorflow_octConv/tf_octConv.py
pointer only (licence: NONE) · get_code("a10e0b743c2016be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zrl4836/tensorflow_octConv when it was checked. 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.

oct_resnet101 Not yet run
unverified (harvested, no recorded run)
d-li14/octconv.pytorch/oct_resnet.py
code served (permissive licence) · get_code("3e3e2d00d1a3acfa")
How it ran

no invocation recorded.

oct_resnet26 Not yet run
unverified (harvested, no recorded run)
d-li14/octconv.pytorch/oct_resnet.py
code served (permissive licence) · get_code("fe3e9e11fca7ea81")
How it ran

no invocation recorded.

oct_resnet50 Not yet run
unverified (harvested, no recorded run)
d-li14/octconv.pytorch/oct_resnet.py
code served (permissive licence) · get_code("b650e259d7bc482b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 34 samples lifted from this paper's linked repositories, 34 carry a function identity and 0 do not. Of the 34 distinct functions with an identity, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 7 later) and 27 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
conv_bn 16 other papers
2 dated earlier, 1 the same month, 13 later
1704.04861 (2017-04)
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.12368 (2019-04)
Towards Efficient Model Compression via Learned Global Ranking
and 13 more not named here
accuracy 10 other papers
1 dated earlier, 9 later
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
2111.02926 (2021-11)
OPENFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion
2111.13470 (2021-11)
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
and 7 more not named here
rerange_index 3 other papers
1 dated earlier, 2 later
1807.11626 (2018-07)
MnasNet: Platform-Aware Neural Architecture Search for Mobile
2111.09883 (2021-11)
Swin Transformer V2: Scaling Up Capacity and Resolution
2204.02557 (2022-04)
MixFormer: Mixing Features across Windows and Dimensions
check_model_file 2 other papers
1 dated earlier, 1 later
1807.11626 (2018-07)
MnasNet: Platform-Aware Neural Architecture Search for Mobile
2111.09883 (2021-11)
Swin Transformer V2: Scaling Up Capacity and Resolution
fast_collate 2 other papers
2 later
1908.09699 (2019-08)
Gated Convolutional Networks with Hybrid Connectivity for Image Classification
2002.11102 (2020-02)
On Feature Normalization and Data Augmentation
similar_architectures 2 other papers
1 dated earlier, 1 later
1807.11626 (2018-07)
MnasNet: Platform-Aware Neural Architecture Search for Mobile
2111.09883 (2021-11)
Swin Transformer V2: Scaling Up Capacity and Resolution
setup_logger 1 other paper
1 later
aaai_20850 (2022 (year only))
Active Learning for Domain Adaptation: An Energy-Based Approach

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

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

Abstract

In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures. Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies. In this work, we propose to factorize the mixed feature maps by their frequencies, and design a novel Octave Convolution (OctConv) operation to store and process feature maps that vary spatially "slower" at a lower spatial resolution reducing both memory and computation cost. Unlike existing multi-scale methods, OctConv is formulated as a single, generic, plug-and-play convolutional unit that can be used as a direct replacement of (vanilla) convolutions without any adjustments in the network architecture. It is also orthogonal and complementary to methods that suggest better topologies or reduce channel-wise redundancy like group or depth-wise convolutions. We experimentally show that by simply replacing convolutions with OctConv, we can consistently boost accuracy for both image and video recognition tasks, while reducing memory and computational cost. An OctConv-equipped ResNet-152 can achieve 82.9% top-1 classification accuracy on ImageNet with merely 22.2 GFLOPs.

For agents

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

get_harvested_code_for_paper("1904.05049")
get_code_for_paper("1904.05049")
have("1904.05049")

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

curl https://syntology.ai/api/ran/1904.05049.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.05049.svg)](https://syntology.ai/paper/1904.05049)

Connect an agent — have() is free.