SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.11129 · 2019

Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 10 have no contract verdict; 2 failures of our instrument; 2 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/1906.11129.json · badge: /api/ran/1906.11129.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
rajeevyasarla/UMRL--using-Cycle-Spinning canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
array2ntpl Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/util.py
code served (permissive licence) · get_code("3819e334fdd1a5bf")
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 Point. 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 collections
import numpy as np

# Create a namedtuple to use as the original
OriginalTuple = collections.namedtuple('Point', ['x', 'y', 'z'])
original_instance = OriginalTuple(x=1, y=2, z=3)

# Convert to array representation using ntpl2array logic
# arr[0] should contain the tuple values
# arr[1] should contain the field names
# arr[2] should contain the class name
arr = np.array([
    (1, 2, 3),  # tuple values
    ('x', 'y', 'z'),  # field names
    'Point'  # class name
], dtype=object)

ARGS = {
    'arr': arr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Point — a Point output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Point output the recorded ndim 1 and dtype family int 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
conv_block Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/models/derain_mulcmp.py
code served (permissive licence) · get_code("0da6b359cfe07ea0")
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 Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_dim": 4,
    "out_dim": 8,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_exp_dir Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/misc.py
code served (permissive licence) · get_code("0f4f2ea321c31cdb")
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 os
import tempfile

# Create a temporary directory path for the experiment
temp_dir = tempfile.gettempdir()
exp_path = os.path.join(temp_dir, "test_exp_dir")

ARGS = {
    "exp": exp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
deconv_block Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/models/derain_mulcmp.py
code served (permissive licence) · get_code("ef2aa4e1449995ca")
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 Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_dim": 3,
    "out_dim": 16,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
default_loader Ran
ran, honoured the contract we drafted
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/classification.py
pointer only (licence: MIT); the stored copy get_code serves, from xlgsyzp/cvpt, is pointer only (licence: NONE) · get_code("ac269a0e4b8d946e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xlgsyzp/cvpt, 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.

getLoader Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/misc.py
code served (permissive licence) · get_code("5e62950b4e5ad9d6")
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 DataLoader. 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.utils.data as data
from unittest.mock import Mock, MagicMock
import os
import tempfile

torch.manual_seed(0)

# Create a minimal mock dataset class that works with DataLoader
class MockDataset(data.Dataset):
    def __init__(self, root, transform=None, seed=None):
        self.root = root
        self.transform = transform
        self.seed = seed
        self.length = 4
    
    def __len__(self):
        return self.length
    
    def __getitem__(self, idx):
        # Return a tuple of (input, target) as expected by pix2pix
        input_tensor = torch.randn(3, 4, 4)
        target_tensor = torch.randn(3, 4, 4)
        if self.transform:
            # Mock transform that just returns tensors
            pass
        return (input_tensor, target_tensor)

# Create mock transform classes
class MockTransform:
    def __call__(self, x):
        return x

class MockCompose:
    def __init__(self, transforms_list):
        self.transforms = transforms_list
    
    def __call__(self, x):
        for t in self.transforms:
            x = t(x)
        return x

class MockRandomHorizontalFlip(MockTransform):
    pass

class MockToTensor(MockTransform):
    pass

class MockNormalize(MockTransform):
    def __init__(self, mean, std):
        self.mean = mean
        self.std = std

# Create mock transforms module
mock_transforms = Mock()
mock_transforms.Compose = MockCompose
mock_transforms.RandomHorizontalFlip = MockRandomHorizontalFlip
mock_transforms.ToTensor = MockToTensor
mock_transforms.Normalize = MockNormalize

# Mock the datasets modules
mock_pix2pix_dataset = MockDataset
mock_pix2pix_val_dataset = MockDataset
mock_pix2pix_class_dataset = MockDataset

# Patch the imports in the function by mocking sys.modules
import sys
sys.modules['datasets'] = Mock()
sys.modules['datasets.pix2pix'] = Mock(pix2pix=mock_pix2pix_dataset)
sys.modules['datasets.pix2pix_val'] = Mock(pix2pix_val=mock_pix2pix_val_dataset)
sys.modules['datasets.pix2pix_class'] = Mock(pix2pix=mock_pix2pix_class_dataset)
sys.modules['transforms'] = Mock()
sys.modules['transforms.pix2pix'] = mock_transforms

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

ARGS = {
    'datasetName': 'pix2pix',
    'dataroot': temp_dir,
    'originalSize': 256,
    'imageSize': 128,
    'batchSize': 2,
    'workers': 0,
    'mean': (0.5, 0.5, 0.5),
    'std': (0.5, 0.5, 0.5),
    'split': 'train',
    'shuffle': True,
    'seed': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
datasets, torch, transforms — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
gradient Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rajeevyasarla/UMRL--using-Cycle-Spinning/umrl_cycspn_train.py
code served (permissive licence) · get_code("70302ac45c91f1c0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function takes a tensor y and computes gradients along spatial dimensions
# y is indexed as y[:, :, :, :-1] and y[:, :, :-1, :], so it's a 4D tensor
# Typical shape: (batch, channels, height, width)
# We need batch=2, and distinct sizes for each dimension

y = torch.randn(2, 3, 5, 4)  # (batch=2, channels=3, height=5, width=4)

ARGS = {
    "y": y
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gram_matrix Ran
ran; our contract draft was wrong, not the code
rajeevyasarla/UMRL--using-Cycle-Spinning/myutils/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from davidpengucf/SFDAHPE, is pointer only (licence: NONE) · get_code("430c582cd8bbb1df")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from davidpengucf/SFDAHPE, 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.

is_image_file Ran
ran, violated the contract we drafted
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/classification.py
pointer only (licence: MIT); the stored copy get_code serves, from sgoldyaev/DeepFashion.ADGAN, is pointer only (licence: NONE) · get_code("ab4109634b75ef8b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from sgoldyaev/DeepFashion.ADGAN, 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.

is_image_file Ran
ran, violated the contract we drafted
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/pix2pix.py
code served (permissive licence) · get_code("9c8620ddd189a741")
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
import torch.nn as nn

# The function is_image_file takes a single parameter: filename
# It checks if the filename ends with any of the image extensions
# We need to provide a string filename that will be tested

ARGS = {
    'filename': 'test_image.jpg'
}
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
make_dataset Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/classification.py
code served (permissive licence) · get_code("afd8d34f939d3de2")
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 os
import tempfile
import shutil

# Create a temporary directory with some image files
temp_dir = tempfile.mkdtemp()

# Create some dummy image files with valid extensions
test_files = ['image1.jpg', 'image2.png', 'image3.jpeg', 'photo.bmp']
for fname in test_files:
    fpath = os.path.join(temp_dir, fname)
    with open(fpath, 'w') as f:
        f.write('dummy image data')

# Also add a non-image file to test filtering
non_image_path = os.path.join(temp_dir, 'readme.txt')
with open(non_image_path, 'w') as f:
    f.write('not an image')

ARGS = {
    'dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
make_dataset Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/pix2pix.py
code served (permissive licence) · get_code("c2b1125a7ec818a5")
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 os
import tempfile
import shutil

# Create a temporary directory with some image files
temp_dir = tempfile.mkdtemp()

# Create some dummy image files
image_files = ['image1.jpg', 'image2.png', 'image3.jpeg', 'photo.bmp']
for fname in image_files:
    fpath = os.path.join(temp_dir, fname)
    with open(fpath, 'w') as f:
        f.write('dummy image data')

# Also create a non-image file to test filtering
non_image_file = os.path.join(temp_dir, 'readme.txt')
with open(non_image_file, 'w') as f:
    f.write('this is not an image')

ARGS = {
    'dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
subtract_imagenet_mean_batch Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/myutils/utils.py
code served (permissive licence) · get_code("e1a6917dbeb17928")
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, 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create a batch of BGR images
# batch size: 2, channels: 3 (BGR), height: 4, width: 5
batch = Variable(torch.randn(2, 3, 4, 5))

ARGS = {
    "batch": batch
}
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, 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: none by the harness; any seed is in the setup block
tensor_load_rgbimage Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/myutils/utils.py
code served (permissive licence) · get_code("78fe823d313a3349")
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 torch
import numpy as np
from PIL import Image
import io

torch.manual_seed(0)

# Create a minimal test image in memory
def create_test_image():
    # Create a small RGB image (4x3 pixels)
    img_array = np.random.randint(0, 256, (3, 4, 3), dtype=np.uint8)
    img = Image.fromarray(img_array.transpose(1, 2, 0), 'RGB')
    # Save to bytes buffer
    buffer = io.BytesIO()
    img.save(buffer, format='PNG')
    buffer.seek(0)
    return buffer

# Create a temporary file-like object
image_buffer = create_test_image()

# We need an actual file path, so create a temporary file
import tempfile
temp_file = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
temp_file.write(image_buffer.getvalue())
temp_file.close()

ARGS = {
    'filename': temp_file.name,
    'size': None,
    'scale': None,
    'keep_asp': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
transpose_ntpl_list Ran
ran on a synthesized input
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/util.py
code served (permissive licence) · get_code("0c1d1c82a2060a88")
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 Point. 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 collections

# Create a simple named tuple type for testing
Point = collections.namedtuple('Point', ['x', 'y', 'z'])

# Create a list of named tuple objects
lst = [
    Point(x=1, y=2, z=3),
    Point(x=4, y=5, z=6),
    Point(x=7, y=8, z=9),
]

ARGS = {
    'lst': lst
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Point — a Point output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Point output the recorded ndim 2 and dtype family int 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
blockUNet1 Not yet run
unverified (harvested, no recorded run)
rajeevyasarla/UMRL--using-Cycle-Spinning/models/derain_mulcmp.py
code served (permissive licence) · get_code("85a3ff2bf90e5a11")
How it ran

no invocation recorded.

ntpl2array Not yet run
unverified (harvested, no recorded run)
rajeevyasarla/UMRL--using-Cycle-Spinning/datasets/util.py
code served (permissive licence) · get_code("f0b5f99e7f243446")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 4 later) and 9 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_image_file 62 other papers
7 dated earlier, 1 the same month, 54 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1703.07511 (2017-03)
Deep Photo Style Transfer
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
and 59 more not named here
default_loader 27 other papers
3 dated earlier, 1 the same month, 23 later
1710.03463 (2017-10)
Learning to Generalize: Meta-Learning for Domain Generalization
1803.08669 (2018-03)
Pyramid Stereo Matching Network
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices
and 24 more not named here
gram_matrix 9 other papers
4 dated earlier, 5 later
1508.06576 (2015-08)
A Neural Algorithm of Artistic Style
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization
and 6 more not named here
gradient 1 other paper
1 later
1907.13106 (2019-07)
Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks
subtract_imagenet_mean_batch 1 other paper
1 dated earlier
1703.06953 (2017-03)
Multi-style Generative Network for Real-time Transfer
tensor_load_rgbimage 1 other paper
1 dated earlier
1703.06953 (2017-03)
Multi-style Generative Network for Real-time Transfer

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

Single image de-raining is an extremely challenging problem since the rainy image may contain rain streaks which may vary in size, direction and density. Previous approaches have attempted to address this problem by leveraging some prior information to remove rain streaks from a single image. One of the major limitations of these approaches is that they do not consider the location information of rain drops in the image. The proposed Uncertainty guided Multi-scale Residual Learning (UMRL) network attempts to address this issue by learning the rain content at different scales and using them to estimate the final de-rained output. In addition, we introduce a technique which guides the network to learn the network weights based on the confidence measure about the estimate. Furthermore, we introduce a new training and testing procedure based on the notion of cycle spinning to improve the final de-raining performance. Extensive experiments on synthetic and real datasets to demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. Code is available at: https://github.com/rajeevyasarla/UMRL--using-Cycle-Spinning

For agents

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

get_harvested_code_for_paper("1906.11129")
get_code_for_paper("1906.11129")
have("1906.11129")

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

curl https://syntology.ai/api/ran/1906.11129.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.11129.svg)](https://syntology.ai/paper/1906.11129)

Connect an agent — have() is free.