SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.00592 · 2019

ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data

arXiv · PDF · Open in the Atlas

Code that ran

7 of 13 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 6 have no contract verdict; 0 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1904.00592.json · badge: /api/ran/1904.00592.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
thimabru1010/ResUnet-a_multitasking community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
Akhilesh64/ResUnet-a community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
yingkaisha/keras-unet-collection reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
Nguyendat-bit/U-net reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
FunctionStatusWhere it lives
Tanimoto_loss Ran
ran on a synthesized input
Akhilesh64/ResUnet-a/loss.py
code served (permissive licence) · get_code("ac254c09046cbb72")
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 SymbolicTensor. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow as tf
import numpy as np

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

# Create small sample tensors
# Shape: (batch_size=2, height=4, width=3, channels=5)
# The function reduces over axes [1, 2] which are spatial dimensions
batch_size = 2
height = 4
width = 3
channels = 5

label = tf.constant(
    np.random.rand(batch_size, height, width, channels).astype(np.float32)
)

pred = tf.constant(
    np.random.rand(batch_size, height, width, channels).astype(np.float32)
)

ARGS = {
    "label": label,
    "pred": pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
compute_mcc Ran
ran on a synthesized input
thimabru1010/ResUnet-a_multitasking/train_ISPRS.py
code served (permissive licence) · get_code("a6948e9f5f9c149e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 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 tensorflow as tf

# Create small TensorFlow tensors for confusion matrix components
tp = tf.constant(50, dtype=tf.float32)
tn = tf.constant(45, dtype=tf.float32)
fp = tf.constant(5, dtype=tf.float32)
fn = tf.constant(8, dtype=tf.float32)

ARGS = {
    "tp": tp,
    "tn": tn,
    "fp": fp,
    "fn": fn,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
get_boundary_label Ran
ran on a synthesized input
thimabru1010/ResUnet-a_multitasking/multitasking_utils.py
code served (permissive licence) · get_code("a6b9928c656450b6")
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 (4, 6, 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 cv2
import numpy as np

# Create a small test label array with shape (height, width, channels)
# Using distinct dimensions: 4 height, 6 width, 3 channels
label = np.random.randint(0, 256, size=(4, 6, 3), dtype=np.uint8)

ARGS = {
    "label": label,
    "kernel_size": (3, 3)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 (4, 6, 3) — shape (4, 6, 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
get_distance_label Ran
ran on a synthesized input
thimabru1010/ResUnet-a_multitasking/multitasking_utils.py
code served (permissive licence) · get_code("8e8a32cb782d2ce1")
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 (4, 3, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import cv2
import numpy as np

# Create a small 3D label array with shape (4, 3, 2)
# Height=4, Width=3, Channels=2
label = np.random.randint(0, 2, size=(4, 3, 2), dtype=np.uint8).astype(np.float32)

# Ensure at least one channel has some non-zero values for distanceTransform to work
label[1:3, 1:2, 0] = 1
label[2:4, 1:3, 1] = 1

ARGS = {
    "label": label
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 (4, 3, 2) — shape (4, 3, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_rgb Ran
ran on a synthesized input
Akhilesh64/ResUnet-a/utils.py
code served (permissive licence) · get_code("4ffac96d4446033c")
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 (4, 3, 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
from sklearn.preprocessing import StandardScaler

# Create a small RGB image: shape (height, width, channels)
# Using distinct dimensions: 4 (height) x 3 (width) x 3 (RGB channels)
img = np.random.rand(4, 3, 3).astype(np.float32)

ARGS = {
    "img": img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 (4, 3, 3) — shape (4, 3, 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
split_pair_names Ran
ran on a synthesized input
Akhilesh64/ResUnet-a/utils.py
code served (permissive licence) · get_code("5f853242800ab2ce")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family 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 tempfile
import os

# Create temporary directories with some dummy files
temp_img_dir = tempfile.mkdtemp()
temp_label_dir = tempfile.mkdtemp()

# Create some dummy image files
for i in range(3):
    with open(os.path.join(temp_img_dir, f'image_{i}.jpg'), 'w') as f:
        f.write('dummy')

# Create corresponding dummy label files
for i in range(3):
    with open(os.path.join(temp_label_dir, f'label_{i}.txt'), 'w') as f:
        f.write('dummy')

ARGS = {
    'img_path': temp_img_dir,
    'label_path': temp_label_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2 — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family 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
str2bool Ran
ran, violated the contract we drafted
thimabru1010/ResUnet-a_multitasking/preprocess_save_patches_Amazon.py
code served (permissive licence) · get_code("7c508037b40522af")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned 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 argparse

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Test cases for str2bool
ARGS = {
    'v': 'true'  # string input that should convert to boolean
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
ResUNET_a_block Not yet run
unverified (harvested, no recorded run)
yingkaisha/keras-unet-collection/keras_unet_collection/_model_resunet_a_2d.py
code served (permissive licence) · get_code("2bedb532bd930b5c")
How it ran

no invocation recorded.

ResUNET_a_right Not yet run
unverified (harvested, no recorded run)
yingkaisha/keras-unet-collection/keras_unet_collection/_model_resunet_a_2d.py
code served (permissive licence) · get_code("d8c07105b75f296b")
How it ran

no invocation recorded.

binarize_matrix Not yet run
unverified (harvested, no recorded run)
Akhilesh64/ResUnet-a/utils.py
code served (permissive licence) · get_code("3f1f2dbfd358b7ab")
How it ran

no invocation recorded.

down_block Not yet run
unverified (harvested, no recorded run)
Nguyendat-bit/U-net/model.py
code served (permissive licence) · get_code("f4fc88dbc53101fa")
How it ran

no invocation recorded.

resunet_a_2d_base Not yet run
unverified (harvested, no recorded run)
yingkaisha/keras-unet-collection/keras_unet_collection/_model_resunet_a_2d.py
code served (permissive licence) · get_code("a36550becdeff22b")
How it ran

no invocation recorded.

up_block Not yet run
unverified (harvested, no recorded run)
Nguyendat-bit/U-net/model.py
code served (permissive licence) · get_code("7ee5caba8c72b702")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 10 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
str2bool 175 other papers
5 dated earlier, 170 later · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
down_block 1 other paper
1 dated earlier
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
up_block 1 other paper
1 dated earlier
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation

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

Scene understanding of high resolution aerial images is of great importance for the task of automated monitoring in various remote sensing applications. Due to the large within-class and small between-class variance in pixel values of objects of interest, this remains a challenging task. In recent years, deep convolutional neural networks have started being used in remote sensing applications and demonstrate state of the art performance for pixel level classification of objects. \textcolor{black}{Here we propose a reliable framework for performant results for the task of semantic segmentation of monotemporal very high resolution aerial images. Our framework consists of a novel deep learning architecture, ResUNet-a, and a novel loss function based on the Dice loss. ResUNet-a uses a UNet encoder/decoder backbone, in combination with residual connections, atrous convolutions, pyramid scene parsing pooling and multi-tasking inference. ResUNet-a infers sequentially the boundary of the objects, the distance transform of the segmentation mask, the segmentation mask and a colored reconstruction of the input. Each of the tasks is conditioned on the inference of the previous ones, thus establishing a conditioned relationship between the various tasks, as this is described through the architecture's computation graph. We analyse the performance of several flavours of the Generalized Dice loss for semantic segmentation, and we introduce a novel variant loss function for semantic segmentation of objects that has excellent convergence properties and behaves well even under the presence of highly imbalanced classes.} The performance of our modeling framework is evaluated on the ISPRS 2D Potsdam dataset. Results show state-of-the-art performance with an average F1 score of 92.9\% over all classes for our best model.

For agents

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

get_harvested_code_for_paper("1904.00592")
get_code_for_paper("1904.00592")
have("1904.00592")

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

curl https://syntology.ai/api/ran/1904.00592.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.00592.svg)](https://syntology.ai/paper/1904.00592)

Connect an agent — have() is free.