SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1409.4842 · 2014

Going deeper with convolutions

Scott Reed, Dragomir Anguelov, Wei Liu, Christian Szegedy, Vincent Vanhoucke, Pierre Sermanet, Andrew Rabinovich, Dumitru Erhan, Yangqing Jia

arXiv · PDF · Open in the Atlas

Code that ran

34 of 42 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (19 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 26 have no contract verdict; 5 failures of our instrument; 8 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/1409.4842.json · badge: /api/ran/1409.4842.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
Mayurji/Image-Classification-PyTorch community
Papers with Code archive
6 ran · 1 no recorded run
0jason000/GoogleNet community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
anguyen8/sam community
Papers with Code archive
4 ran · 0 no recorded run
HolmesShuan/AIM2020-RealSR community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
robin-schneider/cicy-fourfolds community
not in the paper's declared repositories
2 ran · 1 no recorded run
pytorch/vision community
not in the paper's declared repositories
2 ran · 0 no recorded run
zjZSTU/GoogLeNet community
not in the paper's declared repositories
2 ran · 0 no recorded run
lornatang/googlenet-pytorch community
not in the paper's declared repositories
2 ran · 0 no recorded run
Sakib1263/Inception-InceptionResNet-1D-2D-Tensorflow-Keras community
Papers with Code archive
2 ran · 0 no recorded run
cjfghk5697/Pytorch-Research-Paper-Implementations community
Papers with Code archive
2 ran · 0 no recorded run
marload/ConvNets-TensorFlow2 community
not in the paper's declared repositories
1 ran · 0 no recorded run
researchmm/SiamDW community
not in the paper's declared repositories
1 ran · 0 no recorded run
AIOSYM/dl-model-gallery community
Papers with Code archive
1 ran · 0 no recorded run
Jastot/Rodinka_Neural_Network community
Papers with Code archive
1 ran · 0 no recorded run
JasonLiTW/simple-railway-captcha-solver community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
anonymous-koala-supporter/adversarial-deep-metric-learning community
Papers with Code archive
0 ran · 2 no recorded run
sauravmishra1710/Inception---Going-Deeper-with-Convolutions community
not in the paper's declared repositories
0 ran · 1 no recorded run
km1414/CNN-models community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
BasicConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
pytorch/vision/torchvision/models/googlenet.py
code served (permissive licence) · get_code("f5edef376a0cd85e")
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 an instance of its own class, BasicConv2d: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'kernel_size': 3,
    'padding': 1,
}
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 BasicConv2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BasicConv2d 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
BasicConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
anguyen8/sam/madry_files/googlenet.py
pointer only (licence: NONE) · get_code("cb08b86e58d07063")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anguyen8/sam 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.

BasicConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
zjZSTU/GoogLeNet/py/models/googlenet.py
code served (permissive licence) · get_code("03d0214c16636ec8")
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 an instance of its own class, BasicConv2d: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn.functional as F

torch.manual_seed(0)

# BasicConv2d.__init__ takes:
# - in_channels: int
# - out_channels: int
# - **kwargs: additional arguments passed to nn.Conv2d (like kernel_size, stride, padding, etc.)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
}
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 BasicConv2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BasicConv2d 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
BasicConv2d Ran
ran on a synthesized input
lornatang/googlenet-pytorch/model.py
code served (permissive licence) · get_code("624cea5b8980dd04")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 8, 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 torch
import torch.nn as nn
from typing import Any

class BasicConv2d(nn.Module):

    def __init__(self, in_channels: int, out_channels: int, **kwargs: Any) -> None:
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
        self.relu = nn.ReLU(True)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        return out


INIT_ARGS = {
    'in_channels': 3,
    'out_channels': 4,
    'kernel_size': 3,
    'padding': 1,
}

ARGS = {
    'x': torch.randn(2, 3, 8, 8),
}

if __name__ == '__main__':
    model = BasicConv2d(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output dtype: {output.dtype}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float, shape (2, 4, 8, 8) — shape (2, 4, 8, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
BasicConvBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("b0d5748159eb6393")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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_2D_Block Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Sakib1263/Inception-InceptionResNet-1D-2D-Tensorflow-Keras/Codes/Inception_2DCNN.py
code served (permissive licence) · get_code("872e84990e7a5288")
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 KerasTensor. 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

# Create a small input tensor with shape (batch, height, width, channels)
# Using batch=2, height=4, width=3, channels=2
x = tf.keras.Input(shape=(4, 3, 2))

# model_width: number of filters for the Conv2D layer
model_width = 8

# kernel: kernel size for the Conv2D layer
kernel = (3, 3)

# strides: stride configuration (optional, defaults to (1, 1))
strides = (1, 1)

# padding: padding mode (optional, defaults to 'same')
padding = 'same'

ARGS = {
    'x': x,
    'model_width': model_width,
    'kernel': kernel,
    'strides': strides,
    'padding': padding
}
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 KerasTensor — a KerasTensor 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
GoogLeNet Ran
ran on a synthesized input · constructed an object; no result was computed
anguyen8/sam/madry_files/googlenet.py
pointer only (licence: NONE) · get_code("05191308e6a09301")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anguyen8/sam 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.

Inception Ran
ran on a synthesized input · constructed an object; no result was computed
pytorch/vision/torchvision/models/googlenet.py
code served (permissive licence) · get_code("f0189f16534e1298")
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 an instance of its own class, Inception: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'in_channels': 3,
    'ch1x1': 64,
    'ch3x3red': 96,
    'ch3x3': 128,
    'ch5x5red': 16,
    'ch5x5': 32,
    'pool_proj': 32,
    'conv_block': None
}
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 Inception — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Inception 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
Inception Ran
ran on a synthesized input · constructed an object; no result was computed
marload/ConvNets-TensorFlow2/models/GoogLeNet.py
code served (permissive licence) · get_code("3492596d14690fa7")
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 an instance of its own class, Inception: the run constructed the object and did not call it, so no result was computed. 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

# Create a small input tensor for testing
# Shape: (batch_size, height, width, channels)
input_tensor = tf.random.normal((2, 8, 8, 3))

# Define arguments for the Inception layer
# These parameters control the number of filters in each branch
ARGS = {
    'n1x1': 64,           # 1x1 convolution filters
    'n3x3_reduce': 96,    # 1x1 reduction filters before 3x3
    'n3x3': 128,          # 3x3 convolution filters
    'n5x5_reduce': 16,    # 1x1 reduction filters before 5x5
    'n5x5': 32,           # 5x5 convolution filters
    'pool_proj': 32       # projection filters after pooling
}
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 Inception — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Inception 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
Inception Ran
ran on a synthesized input · constructed an object; no result was computed
anguyen8/sam/madry_files/googlenet.py
pointer only (licence: NONE) · get_code("643b86462ac9ae97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anguyen8/sam 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.

Inception Ran
ran on a synthesized input · constructed an object; no result was computed
researchmm/SiamDW/lib/models/modules.py
code served (permissive licence) · get_code("6db662cb8f1b6555")
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 an instance of its own class, Inception: the run constructed the object and did not call it, so no result was computed. 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)

# Define a minimal InceptionM block that matches how it's used in _make_layer
class InceptionM(nn.Module):
    def __init__(self, inchannels, planes, last_relu=True):
        super(InceptionM, self).__init__()
        self.inchannels = inchannels
        self.planes = planes
        self.last_relu = last_relu
        # Simple passthrough convolution to transform channels
        self.conv = nn.Conv2d(inchannels, planes * 5, kernel_size=1, bias=False)
        if last_relu:
            self.relu = nn.ReLU(inplace=True)
    
    def forward(self, x):
        x = self.conv(x)
        if self.last_relu:
            x = self.relu(x)
        return x

# Define ARGS dict with all parameters for Inception.__init__
ARGS = {
    'block': InceptionM,
    'layers': [3, 4]
}
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 Inception — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Inception 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
Inception Ran
ran on a synthesized input · constructed an object; no result was computed
zjZSTU/GoogLeNet/py/models/googlenet.py
code served (permissive licence) · get_code("bb1642b7ac998be9")
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 an instance of its own class, Inception: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'in_channels': 3,
    'ch1x1': 4,
    'ch3x3red': 5,
    'ch3x3': 6,
    'ch5x5red': 7,
    'ch5x5': 8,
    'pool_proj': 9,
    'conv_block': None
}
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 Inception — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Inception 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
Inception Ran
ran on a synthesized input
lornatang/googlenet-pytorch/model.py
code served (permissive licence) · get_code("793b6addc9a83166")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 14, 8, 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 torch
import torch.nn as nn
from typing import Any

# Import the classes
from torch import Tensor

class BasicConv2d(nn.Module):

    def __init__(self, in_channels: int, out_channels: int, **kwargs: Any) -> None:
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
        self.relu = nn.ReLU(True)

    def forward(self, x: Tensor) -> Tensor:
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        return out

class Inception(nn.Module):

    def __init__(self, in_channels: int, ch1x1: int, ch3x3red: int, ch3x3: int, ch5x5red: int, ch5x5: int, pool_proj: int) -> None:
        super(Inception, self).__init__()
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=(1, 1), stride=(1, 1), padding=(0, 0))
        self.branch2 = nn.Sequential(BasicConv2d(in_channels, ch3x3red, kernel_size=(1, 1), stride=(1, 1), padding=(0, 0)), BasicConv2d(ch3x3red, ch3x3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))
        self.branch3 = nn.Sequential(BasicConv2d(in_channels, ch5x5red, kernel_size=(1, 1), stride=(1, 1), padding=(0, 0)), BasicConv2d(ch5x5red, ch5x5, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))
        self.branch4 = nn.Sequential(nn.MaxPool2d(kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), ceil_mode=True), BasicConv2d(in_channels, pool_proj, kernel_size=(1, 1), stride=(1, 1), padding=(0, 0)))

    def forward(self, x: Tensor) -> Tensor:
        branch1 = self.branch1(x)
        branch2 = self.branch2(x)
        branch3 = self.branch3(x)
        branch4 = self.branch4(x)
        out = [branch1, branch2, branch3, branch4]
        out = torch.cat(out, 1)
        return out


INIT_ARGS = {
    'in_channels': 3,
    'ch1x1': 4,
    'ch3x3red': 2,
    'ch3x3': 5,
    'ch5x5red': 2,
    'ch5x5': 3,
    'pool_proj': 2,
}

ARGS = {
    'x': torch.randn(2, 3, 8, 8),
}

if __name__ == '__main__':
    inception = Inception(**INIT_ARGS)
    inception.eval()
    output = inception(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected output channels: {INIT_ARGS['ch1x1'] + INIT_ARGS['ch3x3'] + INIT_ARGS['ch5x5'] + INIT_ARGS['pool_proj']}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float, shape (2, 14, 8, 8) — shape (2, 14, 8, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
InceptionA Ran
ran on a synthesized input · constructed an object; no result was computed
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("8222dc503aa770da")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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.

InceptionAux Ran
ran on a synthesized input · constructed an object; no result was computed
anguyen8/sam/madry_files/googlenet.py
pointer only (licence: NONE) · get_code("ca74dcf9efd4f305")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anguyen8/sam 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.

InceptionB Ran
ran on a synthesized input · constructed an object; no result was computed
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("dbfdca92db85c878")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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.

InceptionC Ran
ran on a synthesized input · constructed an object; no result was computed
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("3bd756253a293db2")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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.

InceptionD Ran
ran on a synthesized input · constructed an object; no result was computed
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("716350814d07123f")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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.

InceptionE Ran
ran on a synthesized input · constructed an object; no result was computed
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("99a8770cbcb4e78e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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.

InceptionModule Ran
ran on a synthesized input · constructed an object; no result was computed
AIOSYM/dl-model-gallery/googlenetv1_pytorch.py
pointer only (licence: NONE) · get_code("dca0f5bb064d3d81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AIOSYM/dl-model-gallery 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.

Inception_block Ran
ran on a synthesized input · constructed an object; no result was computed
cjfghk5697/Pytorch-Research-Paper-Implementations/Vision Models/GoogleNet/models/stl_model.py
code served (permissive licence) · get_code("7639461ad939db84")
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 an instance of its own class, Inception_block: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'in_channels': 3,
    'out_1x1': 64,
    'red_3x3': 96,
    'out_3x3': 128,
    'red_5x5': 16,
    'out_5x5': 32,
    'out_1x1pool': 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 Inception_block — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Inception_block 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
Inceptionv1_Module Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Sakib1263/Inception-InceptionResNet-1D-2D-Tensorflow-Keras/Codes/Inception_2DCNN.py
code served (permissive licence) · get_code("22afed27a328a396")
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) and returned EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 37) 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 input tensor (batch=2, height=4, width=3, channels=5)
input_tensor = tf.random.normal((2, 4, 3, 5))

# Define filter sizes for each branch
filterB1_1 = 8      # Branch 1: 1x1 conv
filterB2_1 = 6      # Branch 2: 1x1 conv
filterB2_2 = 10     # Branch 2: 3x3 conv
filterB3_1 = 4      # Branch 3: 1x1 conv
filterB3_2 = 12     # Branch 3: 5x5 conv
filterB4_1 = 7      # Branch 4 (pool): 1x1 conv
i = 1               # Inception block index

ARGS = {
    'inputs': input_tensor,
    'filterB1_1': filterB1_1,
    'filterB2_1': filterB2_1,
    'filterB2_2': filterB2_2,
    'filterB3_1': filterB3_1,
    'filterB3_2': filterB3_2,
    'filterB4_1': filterB4_1,
    'i': i
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 3, 37) — shape (2, 4, 3, 37) 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
conv2d_bn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
robin-schneider/cicy-fourfolds/inception.py
pointer only (licence: GPL-3.0) · get_code("70e620165414e94c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, robin-schneider/cicy-fourfolds, is not in the permissive set Syntology serves inline. 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_block Ran
ran on a synthesized input · constructed an object; no result was computed
cjfghk5697/Pytorch-Research-Paper-Implementations/Vision Models/GoogleNet/models/stl_model.py
code served (permissive licence) · get_code("30e38658fd407250")
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 an instance of its own class, conv_block: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'kernel_size': 3,
    'padding': 1,
}
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 conv_block — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a conv_block 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
float_parameter Ran
ran, honoured the contract we drafted
0jason000/GoogleNet/src/transforms.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from chenchenzong/dpc, is pointer only (licence: NONE) · get_code("40d3c39a403ae1f7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from chenchenzong/dpc, and GitHub detected no licence in that repository 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.

gaussian_filter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HolmesShuan/AIM2020-RealSR/src/calculate_score.py
code served (permissive licence) · get_code("569f86999a28550f")
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 4, dtype family float, shape (2, 3, 2, 2) 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create input tensor: batch_size=2, channels=3, height=4, width=4
input_tensor = torch.randn(2, 3, 4, 4)

# Create 1-D Gaussian kernel
# The function expects a 4D tensor for conv2d
# Shape should be (out_channels, in_channels/groups, kernel_h, kernel_w)
# Since groups=C (channels), out_channels=C and in_channels/groups=1
# For a 1-D kernel applied as 2D: kernel_h=1, kernel_w=3 (or similar)
gaussian_kernel = torch.tensor([
    [[[0.0625, 0.25, 0.0625]]]  # shape (1, 1, 1, 3) for one channel
], dtype=torch.float32)

# Replicate for each channel (3 channels)
win = gaussian_kernel.repeat(3, 1, 1, 1)  # shape (3, 1, 1, 3)

ARGS = {
    "input": input_tensor,
    "win": win
}
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 4, dtype family float, shape (2, 3, 2, 2) — shape (2, 3, 2, 2) 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
init_group_params Ran
ran on a synthesized input
0jason000/GoogleNet/src/optim.py
code served (permissive licence) · get_code("698131638ff8d4ad")
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 torch.nn as nn

torch.manual_seed(0)

class Param:
    def __init__(self, name):
        self.name = name
        self.data = torch.randn(2, 4)

params = [
    Param('weight'),
    Param('bias'),
    Param('beta'),
    Param('gamma'),
    Param('kernel'),
    Param('scale')
]

weight_decay = 0.01

ARGS = {
    'params': params,
    'weight_decay': weight_decay
}
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 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
int_parameter Ran
ran, honoured the contract we drafted
0jason000/GoogleNet/src/transforms.py
code served (permissive licence) · get_code("e5a370ee6856bd8d")
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 int, ndim 0, dtype family int, 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 numpy as np

ARGS = {
    "level": 5,
    "maxval": 100
}
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 int, ndim 0, dtype family int, 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
is_model Ran
ran, violated the contract we drafted
0jason000/GoogleNet/src/model.py
code served (permissive licence) · get_code("b85a6569fd4f3890")
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.

import torch

# Set up the global model entrypoints dictionary with some test models
_model_entrypoints = {
    'resnet18': 'dummy_model_1',
    'vit_base': 'dummy_model_2',
    'bert_small': 'dummy_model_3'
}

# Define arguments for is_model function
ARGS = {
    'model_name': 'resnet18'
}
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 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
lmse Ran
ran; our contract draft was wrong, not the code
robin-schneider/cicy-fourfolds/inception.py
pointer only (licence: GPL-3.0) · get_code("2566b468b8bbcbe9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, robin-schneider/cicy-fourfolds, is not in the permissive set Syntology serves inline. 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.

model Ran
ran on a synthesized input
Jastot/Rodinka_Neural_Network/py_model/distributed/exp_distr_model.py
pointer only (licence: NONE) · get_code("182b4c3ff5186c04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Jastot/Rodinka_Neural_Network 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.

quantize Ran
ran on a synthesized input
HolmesShuan/AIM2020-RealSR/src/utility.py
code served (permissive licence) · get_code("7185b10fd4807808")
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 4, dtype family float, shape (2, 3, 4, 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

torch.manual_seed(0)

# The function quantizes an image tensor based on an rgb_range parameter
# img: a tensor that will be clamped, rounded, and potentially scaled
# rgb_range: an integer representing the color range (255 or other values)

img = torch.randn(2, 3, 4, 4)  # Small batch of 2 images, 3 channels, 4x4 spatial
rgb_range = 255

ARGS = {
    "img": img,
    "rgb_range": rgb_range,
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 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
ssim Ran
ran on a synthesized input
HolmesShuan/AIM2020-RealSR/src/calculate_score.py
code served (permissive licence) · get_code("d8cbb5697f83debe")
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

torch.manual_seed(0)

# Create sample image tensors
# X and Y: batch of 2, channels of 3, height of 16, width of 16
X = torch.rand(2, 3, 16, 16) * 255.0
Y = torch.rand(2, 3, 16, 16) * 255.0

# Create a custom window (optional parameter)
win = None

ARGS = {
    'X': X,
    'Y': Y,
    'data_range': 255,
    'size_average': True,
    'win_size': 11,
    'win_sigma': 1.5,
    'win': win,
    'K': (0.01, 0.03),
    'nonnegative_ssim': 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 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
toonehot Ran
ran on a synthesized input
JasonLiTW/simple-railway-captcha-solver/demo_cnn.py
code served (permissive licence) · get_code("b1d4cd85ecf614b8")
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 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
import numpy as np

LETTERSTR = '0123456789ABCDEFGHJKLMNPQRSTUVWXYZ'

def toonehot(text):
    labellist = []
    for letter in text:
        onehot = [0 for _ in range(34)]
        num = LETTERSTR.find(letter)
        onehot[num] = 1
        labellist.append(onehot)
    return labellist

# Test with a simple text string containing valid characters
test_text = "ABC123"

ARGS = {
    "text": test_text
}
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 2, dtype family int — 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
GoogLeNet Not yet run
unverified (harvested, no recorded run)
anonymous-koala-supporter/adversarial-deep-metric-learning/pkgs/models/roth.py
pointer only (licence: NONE) · get_code("19cc5d1f21343552")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anonymous-koala-supporter/adversarial-deep-metric-learning 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.

InceptionV1 Not yet run
unverified (harvested, no recorded run)
sauravmishra1710/Inception---Going-Deeper-with-Convolutions/InceptionV1/Inception.py
pointer only (licence: NONE) · get_code("ec0e104006453547")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sauravmishra1710/Inception---Going-Deeper-with-Convolutions 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.

InceptionV3 Not yet run
unverified (harvested, no recorded run)
Mayurji/Image-Classification-PyTorch/InceptionV3.py
pointer only (licence: GPL-3.0) · get_code("b2506f01c4ed156b")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/Image-Classification-PyTorch, is not in the permissive set Syntology serves inline. 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.

calc_psnr Not yet run
unverified (harvested, no recorded run)
HolmesShuan/AIM2020-RealSR/src/calculate_score.py
code served (permissive licence) · get_code("32575c94221a40bf")
How it ran

no invocation recorded.

inception_model Not yet run
unverified (harvested, no recorded run)
robin-schneider/cicy-fourfolds/inception.py
pointer only (licence: GPL-3.0) · get_code("c31382763c8dc15d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, robin-schneider/cicy-fourfolds, is not in the permissive set Syntology serves inline. 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.

inception_module Not yet run
unverified (harvested, no recorded run)
km1414/CNN-models/googlenet-lite/googlenet-lite.py
pointer only (licence: NONE) · get_code("2ee04fba3ac5e1f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, km1414/CNN-models 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.

model_entrypoint Not yet run
unverified (harvested, no recorded run)
0jason000/GoogleNet/src/model.py
code served (permissive licence) · get_code("ac95eb88d9b993fd")
How it ran

no invocation recorded.

rename_attr Not yet run
unverified (harvested, no recorded run)
anonymous-koala-supporter/adversarial-deep-metric-learning/pkgs/models/roth.py
pointer only (licence: NONE) · get_code("f0ea8b21aa7d7f82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anonymous-koala-supporter/adversarial-deep-metric-learning 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.

Also present in other papers' code

Of 42 samples lifted from this paper's linked repositories, 42 carry a function identity and 0 do not. Of the 42 distinct functions with an identity, 6 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 6 later) and 36 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
is_model 22 other papers
22 later
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1911.11907 (2019-11)
GhostNet: More Features from Cheap Operations
and 19 more not named here
float_parameter 15 other papers
15 later
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
and 12 more not named here
int_parameter 8 other papers
8 later
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1911.11907 (2019-11)
GhostNet: More Features from Cheap Operations
and 5 more not named here
init_group_params 5 other papers
5 later
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1911.11907 (2019-11)
GhostNet: More Features from Cheap Operations
and 2 more not named here
model_entrypoint 5 other papers
5 later
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1911.11907 (2019-11)
GhostNet: More Features from Cheap Operations
and 2 more not named here
gaussian_filter 4 other papers
4 later
1611.01704 (2016-11)
End-to-end Optimized Image Compression
2001.01568 (2020-01)
Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
and 1 more not named here

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

We propose a deep convolutional neural network architecture codenamed Inception, which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

For agents

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

get_harvested_code_for_paper("1409.4842")
get_code_for_paper("1409.4842")
have("1409.4842")

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

curl https://syntology.ai/api/ran/1409.4842.json

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

[![Syntology run record](https://syntology.ai/api/ran/1409.4842.svg)](https://syntology.ai/paper/1409.4842)

Connect an agent — have() is free.