SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.02758 · 2018

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

arXiv · PDF · Open in the Atlas

Code that ran

17 of 22 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 16 have no contract verdict; 1 failure of our instrument; 5 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/1807.02758.json · badge: /api/ran/1807.02758.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
Lornatang/CSNLN-PyTorch community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
coloquinte/torchsr reimplementation (classifier label)
classifier basis: classifier_2025
5 ran · 3 no recorded run
ChaofWang/AWSRN unrelated (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
dongheehand/RCAN-tf reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
keerthan2/Residual-Channel-Attention-Network reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
AWMS Ran
ran on a synthesized input · constructed an object; no result was computed
ChaofWang/AWSRN/code/src/model/awsrn.py
code served (permissive licence) · get_code("d19d0c8792f5b99a")
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, AWMS: 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)

# Create a simple args object with n_colors attribute
class ArgsConfig:
    def __init__(self):
        self.n_colors = 3

# Create a simple weight normalization wrapper function
def simple_wn(module):
    return module

# Define all arguments for AWMS
ARGS = {
    'args': ArgsConfig(),
    'scale': 2,
    'n_feats': 4,
    'kernel_size': 3,
    'wn': simple_wn
}
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 AWMS — 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 AWMS 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
AWRU Ran
ran on a synthesized input · constructed an object; no result was computed
ChaofWang/AWSRN/code/src/model/awsrn.py
code served (permissive licence) · get_code("2ec67cec615644ea")
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, AWRU: 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)

# Weight normalization wrapper - used as the `wn` parameter
class WeightNorm(nn.Module):
    def __init__(self, module):
        super().__init__()
        self.module = module
    
    def forward(self, x):
        return self.module(x)

def wn(module):
    """Weight normalization function that wraps a module"""
    return WeightNorm(module)

# Define ARGS dict with all parameters for AWRU.__init__
ARGS = {
    'n_feats': 4,           # number of input/output features
    'kernel_size': 3,       # convolution kernel size
    'block_feats': 8,       # intermediate feature dimension (different from n_feats)
    'wn': wn,               # weight normalization function
    'res_scale': 1,         # residual scaling factor
    'act': nn.ReLU(True)    # activation 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 AWRU — 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 AWRU 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
LFB Ran
ran on a synthesized input · constructed an object; no result was computed
ChaofWang/AWSRN/code/src/model/awsrn.py
code served (permissive licence) · get_code("1d26ee244b0e0aa3")
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, LFB: 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)

# Weight normalization wrapper
class WeightNorm(nn.Module):
    def __init__(self, module):
        super().__init__()
        self.module = module
    
    def forward(self, x):
        return self.module(x)

def wn(module):
    return WeightNorm(module)

# Build the arguments dict
ARGS = {
    'n_feats': 4,
    'kernel_size': 3,
    'block_feats': 8,
    'wn': wn,
    'act': nn.ReLU(True),
}
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 LFB — 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 LFB 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
MODEL Ran
ran on a synthesized input · constructed an object; no result was computed
ChaofWang/AWSRN/code/src/model/awsrn.py
code served (permissive licence) · get_code("c81b412e3e5ff687")
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, MODEL: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

class Args:
    def __init__(self):
        self.scale = [2]  # upscaling factor
        self.n_resblocks = 2  # number of residual blocks
        self.n_feats = 4  # number of features
        self.n_colors = 3  # RGB channels
        self.block_feats = 4  # features in residual blocks

ARGS = {
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MODEL — 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 MODEL 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
MeanShift Ran
ran on a synthesized input
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("8affcfa340387a49")
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, 3, 4, 5) 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

class MeanShift(nn.Conv2d):

    def __init__(self, rgb_range, rgb_mean=(0.4488, 0.4371, 0.404), rgb_std=(1.0, 1.0, 1.0), sign=-1):
        super(MeanShift, self).__init__(3, 3, kernel_size=1)
        std = torch.Tensor(rgb_std)
        self.weight.data = torch.eye(3).view(3, 3, 1, 1) / std.view(3, 1, 1, 1)
        self.bias.data = sign * rgb_range * torch.Tensor(rgb_mean) / std
        for p in self.parameters():
            p.requires_grad = False


INIT_ARGS = {
    'rgb_range': 255,
    'rgb_mean': (0.4488, 0.4371, 0.404),
    'rgb_std': (1.0, 1.0, 1.0),
    'sign': -1
}

ARGS = {
    'input': torch.randn(2, 3, 4, 5)
}

if __name__ == '__main__':
    model = MeanShift(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['input'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output:\n{output}")
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, 3, 4, 5) — shape (2, 3, 4, 5) 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)
RCAN Ran
ran on a synthesized input
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("7c4c09142bd8b3be")
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; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

INIT_ARGS = {
    'n_resgroups': 2,
    'n_resblocks': 2,
    'n_feats': 4,
    'reduction': 2,
    'scale': 2,
    'pretrained': False,
    'map_location': None
}

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

ARGS = {
    'x': input_tensor,
    'scale': None
}
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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)
ResidualGroup Ran
ran on a synthesized input
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("464cf568ffdadee9")
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; 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

def default_conv(in_channels, out_channels, kernel_size, bias=True):
    return nn.Conv2d(in_channels, out_channels, kernel_size, padding=(kernel_size//2), bias=bias)

INIT_ARGS = {
    'conv': default_conv,
    'n_feat': 8,
    'kernel_size': 3,
    'reduction': 4,
    'act': nn.ReLU(True),
    'n_resblocks': 2
}

ARGS = {
    'x': torch.randn(2, 8, 16, 12)
}
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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)
Scale Ran
ran on a synthesized input · constructed an object; no result was computed
ChaofWang/AWSRN/code/src/model/awsrn.py
code served (permissive licence) · get_code("1feb1832e4fe7f2e")
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, Scale: 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)

class Scale(nn.Module):

    def __init__(self, init_value=0.001):
        super().__init__()
        self.scale = nn.Parameter(torch.FloatTensor([init_value]))

    def forward(self, input):
        return input * self.scale


ARGS = {
    'init_value': 0.001
}
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 Scale — 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 Scale 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
Upsampler Ran
ran on a synthesized input
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("8f95f5fc9a5bc070")
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, 32, 32) 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 math
import torch
import torch.nn as nn

class Upsampler(nn.Sequential):

    def __init__(self, conv, scale, n_feats, bn=False, act=False, bias=True):
        m = []
        if scale & scale - 1 == 0:
            for _ in range(int(math.log(scale, 2))):
                m.append(conv(n_feats, 4 * n_feats, 3, bias))
                m.append(nn.PixelShuffle(2))
                if bn:
                    m.append(nn.BatchNorm2d(n_feats))
                if act == 'relu':
                    m.append(nn.ReLU(True))
                elif act == 'prelu':
                    m.append(nn.PReLU(n_feats))
        elif scale == 3:
            m.append(conv(n_feats, 9 * n_feats, 3, bias))
            m.append(nn.PixelShuffle(3))
            if bn:
                m.append(nn.BatchNorm2d(n_feats))
            if act == 'relu':
                m.append(nn.ReLU(True))
            elif act == 'prelu':
                m.append(nn.PReLU(n_feats))
        else:
            raise NotImplementedError
        super(Upsampler, self).__init__(*m)


def default_conv(in_channels, out_channels, kernel_size, bias=True):
    return nn.Conv2d(in_channels, out_channels, kernel_size, padding=kernel_size//2, bias=bias)


INIT_ARGS = {
    'conv': default_conv,
    'scale': 4,
    'n_feats': 4,
    'bn': False,
    'act': 'relu',
    'bias': True
}

ARGS = {
    'input': torch.randn(2, 4, 8, 8)
}

if __name__ == '__main__':
    upsampler = Upsampler(**INIT_ARGS)
    output = upsampler(**ARGS)
    print(f"Input shape: {ARGS['input'].shape}")
    print(f"Output shape: {output.shape}")
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, 32, 32) — shape (2, 4, 32, 32) 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)
dataloader Ran
ran on a synthesized input · constructed an object; no result was computed
dongheehand/RCAN-tf/RCA_net.py
pointer only (licence: NONE) · get_code("c214ddcde10c7d20")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dongheehand/RCAN-tf 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.

default_conv Ran
ran; our contract draft was wrong, not the code
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("8b0e794d4d8f9b13")
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)

ARGS = {
    'in_channels': 3,
    'out_channels': 5,
    'kernel_size': 3,
    'bias': True
}
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
extract_image_patches Ran
ran on a synthesized input
Lornatang/CSNLN-PyTorch/model.py
code served (permissive licence) · get_code("2b097a5a42ea2d85")
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 3, dtype family float, shape (2, 27, 64) 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)

ARGS = {
    "images": torch.randn(2, 3, 8, 8),
    "kernel_size": [3, 3],
    "stride": [1, 1],
    "rates": [1, 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 Tensor, ndim 3, dtype family float, shape (2, 27, 64) — shape (2, 27, 64) 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
image2tensor Ran
ran on a synthesized input
Lornatang/CSNLN-PyTorch/imgproc.py
code served (permissive licence) · get_code("d22766d95ec24b98")
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 3, dtype family float, shape (3, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch
from torchvision.transforms import functional as F

torch.manual_seed(0)

# Create a small test image as numpy array with values in [0, 255] range
# Using shape (height, width, channels) as typical for OpenCV imread output
example_image = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

ARGS = {
    "image": example_image,
    "range_norm": True,
    "half": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 4, 3) — shape (3, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
image_resize Ran
ran on a synthesized input
Lornatang/CSNLN-PyTorch/imgproc.py
code served (permissive licence) · get_code("ce1b9b76c304d922")
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 3, dtype family float, shape (8, 10, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import math

torch.manual_seed(0)

# Create a small test image (3 channels, 4 height, 5 width)
image_np = np.random.rand(4, 5, 3).astype(np.float32)

# Define arguments for image_resize function
ARGS = {
    'image': image_np,
    'scale_factor': 2.0,
    'antialiasing': True
}
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 ndarray, ndim 3, dtype family float, shape (8, 10, 3) — shape (8, 10, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reduce_sum Ran
ran on a synthesized input
Lornatang/CSNLN-PyTorch/model.py
code served (permissive licence) · get_code("f9555708bbf55bd4")
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 a small tensor with distinct dimensions for testing
x = torch.randn(2, 3, 4, 5)

# Test different parameter combinations
ARGS = {
    "x": x,
    "axis": None,
    "keepdim": 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
same_padding Ran
ran on a synthesized input
Lornatang/CSNLN-PyTorch/model.py
code served (permissive licence) · get_code("4373e1ddd1bd3573")
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, 7, 9) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a 4D tensor for images: (batch_size, channels, height, width)
images = torch.randn(2, 3, 5, 7)

# Define kernel_size as a list of two integers (height, width)
kernel_size = [3, 3]

# Define stride as a list of two integers (height, width)
stride = [1, 1]

# Define rates (dilation rates) as a list of two integers (height, width)
rates = [1, 1]

ARGS = {
    "images": images,
    "kernel_size": kernel_size,
    "stride": stride,
    "rates": rates
}
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, 7, 9) — shape (2, 3, 7, 9) 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
tensor2image Ran
ran on a synthesized input
Lornatang/CSNLN-PyTorch/imgproc.py
code served (permissive licence) · get_code("dd73a13fd75b72d0")
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 3, dtype family int, shape (4, 5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a small NCHW tensor with values in [0, 1] range
# N=1 (batch), C=3 (channels), H=4 (height), W=5 (width)
tensor = torch.rand(1, 3, 4, 5)

ARGS = {
    "tensor": tensor,
    "range_norm": False,
    "half": False
}
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 ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
RCAB Not yet run
unverified (harvested, no recorded run)
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("c618cce8b87eb8fe")
How it ran

no invocation recorded.

RCA_net Not yet run
unverified (harvested, no recorded run)
dongheehand/RCAN-tf/RCA_net.py
pointer only (licence: NONE) · get_code("916710c01e731111")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dongheehand/RCAN-tf 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_fn Not yet run
unverified (harvested, no recorded run)
keerthan2/Residual-Channel-Attention-Network/code/model.py
pointer only (licence: NONE) · get_code("345a6af0c359845e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, keerthan2/Residual-Channel-Attention-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. No invocation recorded.

rcan Not yet run
unverified (harvested, no recorded run)
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("38ca3bbb2a93c9d9")
How it ran

no invocation recorded.

rcan_g10r20f64 Not yet run
unverified (harvested, no recorded run)
coloquinte/torchsr/torchsr/models/rcan.py
code served (permissive licence) · get_code("de5bafbf7df67a7f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 later) and 16 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
default_conv
brick of this paper's assembly: helper
57 other papers
4 dated earlier, 53 later · 2 only as an assembly brick
1707.02921 (2017-07)
Enhanced Deep Residual Networks for Single Image Super-Resolution
1803.02735 (2018-03)
Deep Back-Projection Networks For Super-Resolution
1803.04626 (2018-03)
Maintaining Natural Image Statistics with the Contextual Loss
and 54 more not named here
MeanShift
brick of this paper's assembly: helper
3 other papers
3 later
2203.04963 (2022-03)
Neural Data-Dependent Transform for Learned Image Compression
2203.06697 (2022-03)
Efficient Long-Range Attention Network for Image Super-resolution
2303.16890 (2023-03)
DPF: Learning Dense Prediction Fields with Weak Supervision
Upsampler
brick of this paper's assembly: model
2 other papers
2 later
2303.16890 (2023-03)
DPF: Learning Dense Prediction Fields with Weak Supervision
2309.04803 (2023-09)
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
image2tensor 2 other papers
1 dated earlier, 1 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
2005.12597 (2020-05)
Perceptual Extreme Super Resolution Network with Receptive Field Block
image_resize 2 other papers
1 dated earlier, 1 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
2005.12597 (2020-05)
Perceptual Extreme Super Resolution Network with Receptive Field Block
tensor2image 2 other papers
1 dated earlier, 1 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
2005.12597 (2020-05)
Perceptual Extreme Super Resolution Network with Receptive Field Block

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

Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections. Each residual group contains some residual blocks with short skip connections. Meanwhile, RIR allows abundant low-frequency information to be bypassed through multiple skip connections, making the main network focus on learning high-frequency information. Furthermore, we propose a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Extensive experiments show that our RCAN achieves better accuracy and visual improvements against state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("1807.02758")
get_code_for_paper("1807.02758")
have("1807.02758")

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

curl https://syntology.ai/api/ran/1807.02758.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.02758.svg)](https://syntology.ai/paper/1807.02758)

Connect an agent — have() is free.