SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1504.06375 · 2015

Holistically-Nested Edge Detection

arXiv · PDF · Open in the Atlas

Code that ran

13 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, 0 violated it and 13 have no contract verdict; 0 failures 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/1504.06375.json · badge: /api/ran/1504.06375.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
meteorshowers/hed-pytorch community (classifier label)
classifier basis not recorded on the link
9 ran · 0 no recorded run
alessandrozamberletti/docdetect community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
crop Ran
ran on a synthesized input
meteorshowers/hed-pytorch/models.py
code served (permissive licence) · get_code("d65fe0ebd97691cf")
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, 4, 5, 6) 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 with shape (batch, channels, height, width)
# Using distinct sizes: batch=2, channels=4, height=7, width=9
variable = torch.randn(2, 4, 7, 9)

# Define crop parameters
th = 5  # target height
tw = 6  # target width

ARGS = {
    'variable': variable,
    'th': th,
    'tw': tw
}
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, 4, 5, 6) — shape (2, 4, 5, 6) 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
cross_entropy_loss Ran
ran on a synthesized input
meteorshowers/hed-pytorch/functions.py
code served (permissive licence) · get_code("508c627527d31817")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create prediction tensor - should be float values suitable for binary cross entropy
# Shape: (batch_size=2, features=4)
prediction = torch.rand(2, 4)

# Create label tensor - should contain integer values where 0 is negative class, 1+ is positive
# Shape: (batch_size=2, features=4)
label = torch.tensor([[0, 1, 1, 0], [1, 0, 1, 1]])

ARGS = {
    "prediction": prediction,
    "label": label,
}
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
detect_edges Ran
ran on a synthesized input
alessandrozamberletti/docdetect/docdetect/canny_edges.py
code served (permissive licence) · get_code("aa939b7dad7d70d5")
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 int, shape (50, 40) 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 image (BGR format for OpenCV)
# Using distinct dimensions: height=50, width=40, channels=3
im = np.random.randint(0, 256, (50, 40, 3), dtype=np.uint8)

ARGS = {
    "im": im,
    "blur_radius": 5,
    "thr1": 100,
    "thr2": 200,
    "remove_text": True,
}
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 2, dtype family int, shape (50, 40) — shape (50, 40) 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
detect_lines Ran
ran on a synthesized input
alessandrozamberletti/docdetect/docdetect/hough_lines.py
code served (permissive licence) · get_code("ad3921821e7197a9")
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 cv2
import numpy as np
import math

# Create a small test image for HoughLines detection
# HoughLines expects a binary image (CV_8U)
test_image = np.zeros((100, 100), dtype=np.uint8)
# Draw some lines in the image
cv2.line(test_image, (10, 10), (90, 90), 255, 2)
cv2.line(test_image, (10, 90), (90, 10), 255, 2)

ARGS = {
    "im": test_image,
    "hough_thr": 65,
    "group_similar_thr": 30
}
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 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
draw Ran
ran on a synthesized input
alessandrozamberletti/docdetect/docdetect/processor.py
code served (permissive licence) · get_code("628f3b8a5f4d8e08")
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 (100, 100, 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 image (BGR format for cv2)
im = np.zeros((100, 100, 3), dtype=np.uint8)

# Create some rectangles as lists of (x, y) tuples
# Rectangle 1: small rectangle
rect1 = [(10, 10), (30, 10), (30, 30), (10, 30)]

# Rectangle 2: larger rectangle
rect2 = [(40, 40), (80, 40), (80, 90), (40, 90)]

rects = [rect1, rect2]

ARGS = {
    "rects": rects,
    "im": im,
    "debug": False
}
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 int, shape (100, 100, 3) — shape (100, 100, 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
find_quadrilaterals Ran
ran on a synthesized input
alessandrozamberletti/docdetect/docdetect/quadrilaterals.py
code served (permissive licence) · get_code("fe7c0f1a0492471b")
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 3, 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 itertools

def _cycles2coords(cycles, intersections):
    return [[_node2coords(node, intersections) for node in quadrilateral] for quadrilateral in cycles]

def _node2coords(node, intersections):
    return next((corner['coords'] for corner in intersections if corner['id'] == node))

def _build_graph(intersections):
    graph = {k['id']: [] for k in intersections}
    for i1, i2 in itertools.permutations(intersections, 2):
        if _common_line_exists(i1['lines'], i2['lines']):
            graph[i1['id']].append(i2['id'])
    return graph

def _common_line_exists(l1, l2):
    common_line = set(list(l1)) & set(list(l2))
    return True if common_line else False

def _bounded_dfs(neighbours, current, loops, seen=[]):
    if current in seen:
        return
    seen.append(current)
    if len(seen) == 4:
        _add_if_loop(current, neighbours, seen, loops)
    else:
        [_bounded_dfs(neighbours, neighbour, loops, seen=seen) for neighbour in neighbours[current]]
    del seen[-1]

def _add_if_loop(current, neighbours, seen, cycles):
    if seen[0] in neighbours[current]:
        cycles.append(tuple(seen))

def find_quadrilaterals(intersections):
    graph = _build_graph(intersections)
    loops = []
    [_bounded_dfs(graph, node, loops) for node in graph]
    return _cycles2coords(loops, intersections)

ARGS = {
    'intersections': [
        {
            'id': 0,
            'coords': (0.0, 0.0),
            'lines': [1, 2]
        },
        {
            'id': 1,
            'coords': (1.0, 0.0),
            'lines': [1, 3]
        },
        {
            'id': 2,
            'coords': (1.0, 1.0),
            'lines': [2, 3]
        },
        {
            'id': 3,
            'coords': (0.0, 1.0),
            'lines': [2, 3]
        }
    ]
}
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 3, 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
interp_surgery Ran
ran on a synthesized input
meteorshowers/hed-pytorch/models.py
code served (permissive licence) · get_code("135486a95911e46f")
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, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    'in_channels': 3,
    'out_channels': 3,
    'h': 4,
    'w': 4
}
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, 4, 4) — shape (3, 3, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_pretrained Ran
ran on a synthesized input
meteorshowers/hed-pytorch/utils.py
code served (permissive licence) · get_code("b3d81e689671b903")
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, 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 sys
import torch
import torch.nn as nn
import tempfile

torch.manual_seed(0)

# Create a minimal model
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal optimizer
model = MinimalModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a temporary checkpoint file
checkpoint = {
    'state_dict': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'epoch': 5
}

with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.pt') as f:
    checkpoint_path = f.name

torch.save(checkpoint, checkpoint_path)

# Create fresh model and optimizer for loading
fresh_model = MinimalModel()
fresh_optimizer = torch.optim.SGD(fresh_model.parameters(), lr=0.01)

ARGS = {
    'model': fresh_model,
    'fname': checkpoint_path,
    'optimizer': fresh_optimizer
}
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, ndim 1, dtype family float — a tuple 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
prepare_image Ran
ran on a synthesized input
meteorshowers/hed-pytorch/data_loader.py
code served (permissive licence) · get_code("d252c37318502755")
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 (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 numpy as np

# Create a small test image with shape (height, width, channels)
# Using distinct dimensions: 4x5x3 (height x width x RGB channels)
im = np.random.randint(0, 256, size=(4, 5, 3), dtype=np.uint8).astype(np.float32)

ARGS = {
    "im": im
}
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 (3, 4, 5) — shape (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
prepare_image_cv2 Ran
ran on a synthesized input
meteorshowers/hed-pytorch/data_loader.py
code served (permissive licence) · get_code("ebdf723bf680cac4")
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 (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 numpy as np

# Create a sample image with shape (height, width, 3) for RGB
# Using shape (4, 5, 3) to have distinct dimensions
height, width, channels = 4, 5, 3
im = np.random.rand(height, width, channels).astype(np.float32) * 255

ARGS = {
    "im": im
}
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 (3, 4, 5) — shape (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
sigmoid_cross_entropy_loss Ran
ran on a synthesized input
meteorshowers/hed-pytorch/functions.py
code served (permissive licence) · get_code("e939917d68cfb910")
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 small tensors for the function
# prediction: logits (unbounded values, will be passed through sigmoid in BCE)
# label: binary labels (0 or 1)

batch_size = 2
num_features = 4

prediction = torch.randn(batch_size, num_features)
label = torch.randint(0, 2, (batch_size, num_features))

ARGS = {
    "prediction": prediction,
    "label": label,
}
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
upsample_filt Ran
ran on a synthesized input
meteorshowers/hed-pytorch/models.py
code served (permissive licence) · get_code("c9519ae7724e4642")
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 (5, 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 numpy as np

def upsample_filt(size):
    factor = (size + 1) // 2
    if size % 2 == 1:
        center = factor - 1
    else:
        center = factor - 0.5
    og = np.ogrid[:size, :size]
    return (1 - abs(og[0] - center) / factor) * (1 - abs(og[1] - center) / factor)

ARGS = {
    "size": 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 (5, 5) — shape (5, 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
weighted_nll_loss Ran
ran on a synthesized input
meteorshowers/hed-pytorch/functions.py
code served (permissive licence) · get_code("65d2e849b8727187")
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)

# Analyze the function:
# - prediction: used with .shape[1] to get nch (number of channels)
#   passed to nll_loss which expects (N, C) for class probabilities
#   Should be log probabilities from LogSoftmax
# - label: squeezed on dim=0, converted to long, compared with nch
#   passed to nll_loss which expects (N,) class indices
#   Values should be in range [0, nch)

# Create small tensors
batch_size = 2
num_classes = 4

# prediction: (batch_size, num_classes) with log probabilities
# Using log_softmax to get proper log probabilities for nll_loss
prediction = torch.log_softmax(torch.randn(batch_size, num_classes), dim=1)

# label: (1, batch_size) which will be squeezed to (batch_size,)
# Values should be class indices in range [0, num_classes)
label = torch.randint(0, num_classes, (1, batch_size))

ARGS = {
    "prediction": prediction,
    "label": label,
}
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

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, 8 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 8 later) and 5 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
crop 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
cross_entropy_loss 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
interp_surgery 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
load_pretrained 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
prepare_image 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
prepare_image_cv2 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
sigmoid_cross_entropy_loss 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform
upsample_filt 1 other paper
1 later
2001.06570 (2020-01)
Harmonic Convolutional Networks based on Discrete Cosine Transform

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

We develop a new edge detection algorithm that tackles two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Our proposed method, holistically-nested edge detection (HED), performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to approach the human ability resolve the challenging ambiguity in edge and object boundary detection. We significantly advance the state-of-the-art on the BSD500 dataset (ODS F-score of .782) and the NYU Depth dataset (ODS F-score of .746), and do so with an improved speed (0.4 second per image) that is orders of magnitude faster than some recent CNN-based edge detection algorithms.

For agents

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

get_harvested_code_for_paper("1504.06375")
get_code_for_paper("1504.06375")
have("1504.06375")

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

curl https://syntology.ai/api/ran/1504.06375.json

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

[![Syntology run record](https://syntology.ai/api/ran/1504.06375.svg)](https://syntology.ai/paper/1504.06375)

Connect an agent — have() is free.