SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.09221 · 2019

Progressive Image Deraining Networks: A Better and Simpler Baseline

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 7 have no contract verdict; 1 failure of our instrument; 0 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/1901.09221.json · badge: /api/ran/1901.09221.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
GuoQuanhao/PRNet-Paddle community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
simonsLiang/PReNet_paddle community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Im2Patch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GuoQuanhao/PRNet-Paddle/DerainDataset.py
code served (permissive licence) · get_code("2af2ba98f984835a")
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 4, dtype family float, shape (3, 3, 3, 24) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small test image tensor
# Shape: (channels, width, height)
# Using distinct sizes: 3 channels, 8x6 spatial dimensions
img = np.random.rand(3, 8, 6).astype(np.float32)

# Window size for patching
win = 3

# Stride for patch extraction
stride = 1

ARGS = {
    "img": img,
    "win": win,
    "stride": stride
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (3, 3, 3, 24) — shape (3, 3, 3, 24) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
batch_PSNR Ran
ran on a synthesized input
GuoQuanhao/PRNet-Paddle/utils.py
code served (permissive licence) · get_code("a8d4fcacf0698a54")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create small tensor arguments for batch_PSNR
# The function expects tensors with .cpu() and .numpy() methods
# Shape: (batch_size, channels, height, width) = (2, 3, 4, 5)
img = torch.rand(2, 3, 4, 5)
imclean = torch.rand(2, 3, 4, 5)
data_range = 1.0

ARGS = {
    "img": img,
    "imclean": imclean,
    "data_range": data_range,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
findLastCheckpoint Ran
ran on a synthesized input
GuoQuanhao/PRNet-Paddle/utils.py
code served (permissive licence) · get_code("d3f67087567e318c")
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 os
import tempfile
import shutil

# Create a temporary directory with mock checkpoint files
temp_dir = tempfile.mkdtemp()

# Create mock checkpoint files with epoch numbers in their names
checkpoint_files = [
    os.path.join(temp_dir, 'model_epoch5.pdparams'),
    os.path.join(temp_dir, 'model_epoch10.pdparams'),
    os.path.join(temp_dir, 'model_epoch3.pdparams'),
]

for filepath in checkpoint_files:
    with open(filepath, 'w') as f:
        f.write('mock checkpoint')

ARGS = {
    'save_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 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
findLastCheckpoint Ran
ran on a synthesized input
simonsLiang/PReNet_paddle/utils.py
code served (permissive licence) · get_code("a96487f60124693f")
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 os
import tempfile
import shutil

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

# Create some fake checkpoint files with epoch numbers in their names
checkpoint_files = [
    os.path.join(temp_dir, 'model_epoch5.pth'),
    os.path.join(temp_dir, 'model_epoch10.pth'),
    os.path.join(temp_dir, 'model_epoch3.pth'),
]

# Create the files
for filepath in checkpoint_files:
    with open(filepath, 'w') as f:
        f.write('fake checkpoint')

# Define the arguments dictionary
ARGS = {
    'save_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 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
gauss_filter Ran
ran on a synthesized input
GuoQuanhao/PRNet-Paddle/statistic/evaluate.py
code served (permissive licence) · get_code("fdfa74ba00e702c9")
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 2, dtype family float, shape (11, 11) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "kernel_size": 11,
    "sigma": 1.5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (11, 11) — shape (11, 11) 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
matlab_psnr Ran
ran on a synthesized input
GuoQuanhao/PRNet-Paddle/statistic/evaluate.py
code served (permissive licence) · get_code("6f10c4ac5f5970e6")
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 float, 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 numpy as np
import math

torch_imported = False
try:
    import torch
    torch_imported = True
except:
    pass

# Create two small numpy arrays representing images
# Using distinct shapes: 2x4x3 for img1 and 2x4x3 for img2
# to represent batch of 2 images with height 4 and width 3
np.random.seed(0)
img1 = np.random.rand(2, 4, 3).astype(np.float32)
img2 = np.random.rand(2, 4, 3).astype(np.float32) + 0.1  # Slightly different

ARGS = {
    'img1': img1,
    'img2': img2,
}
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 float, 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
normalize Ran
ran, violated the contract we drafted
simonsLiang/PReNet_paddle/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from zhihefang/SFGNet, is pointer only (licence: NONE) · get_code("5dfad570b582b1ea")
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 zhihefang/SFGNet, 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.

rgb2ycbcr Ran
ran on a synthesized input
GuoQuanhao/PRNet-Paddle/statistic/evaluate.py
code served (permissive licence) · get_code("925b86fff89dd565")
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 (2, 2, 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

# Create a small RGB image (height=2, width=3, channels=3)
# RGB values should be in range [0, 255]
rgb_img = np.array([
    [[255, 0, 0], [0, 255, 0]],
    [[0, 0, 255], [128, 128, 128]]
], dtype=np.float32)

ARGS = {
    "rgb_img": rgb_img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 2, 3) — shape (2, 2, 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
shave Ran
ran on a synthesized input
simonsLiang/PReNet_paddle/mutils.py
code served (permissive licence) · get_code("0a2256a291767ded")
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 (6, 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

torch.manual_seed(0)

# The function shave takes an image array and removes borders
# It uses standard numpy/array indexing: im[border[0]:-border[0], border[1]:-border[1], ...]
# The 'im' parameter should be an array-like object supporting slicing
# The 'border' parameter should be an integer

# Create a small image array with distinct dimensions
# Shape: (height, width, channels) = (10, 8, 3)
im = np.random.rand(10, 8, 3)

# Border size as integer
border = 2

ARGS = {
    "im": im,
    "border": border,
}
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 (6, 4, 3) — shape (6, 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

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
Im2Patch 5 other papers
1 dated earlier, 4 later
1608.03981 (2016-08)
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
1907.03029 (2019-07)
Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
2006.05082 (2020-06)
Learning to Stop While Learning to Predict
and 2 more not named here
normalize 4 other papers
1 dated earlier, 3 later
1608.03981 (2016-08)
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
1907.03029 (2019-07)
Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
2006.05082 (2020-06)
Learning to Stop While Learning to Predict
and 1 more not named here
shave 1 other paper
1 later
1909.11856 (2019-09)
Lightweight Image Super-Resolution with Information Multi-distillation Network

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

Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced to exploit the dependencies of deep features across stages, forming our progressive recurrent network (PReNet). Furthermore, intra-stage recursive computation of ResNet can be adopted in PRN and PReNet to notably reduce network parameters with graceful degradation in deraining performance. For network input and output, we take both stage-wise result and original rainy image as input to each ResNet and finally output the prediction of {residual image}. As for loss functions, single MSE or negative SSIM losses are sufficient to train PRN and PReNet. Experiments show that PRN and PReNet perform favorably on both synthetic and real rainy images. Considering its simplicity, efficiency and effectiveness, our models are expected to serve as a suitable baseline in future deraining research. The source codes are available at https://github.com/csdwren/PReNet.

For agents

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

get_harvested_code_for_paper("1901.09221")
get_code_for_paper("1901.09221")
have("1901.09221")

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

curl https://syntology.ai/api/ran/1901.09221.json

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

[![Syntology run record](https://syntology.ai/api/ran/1901.09221.svg)](https://syntology.ai/paper/1901.09221)

Connect an agent — have() is free.