SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.05591 · 2018

Towards End-to-End Lane Detection: an Instance Segmentation Approach

arXiv · PDF · Open in the Atlas

Code that ran

16 of 34 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; 2 honoured the contract we drafted, 1 violated it and 12 have no contract verdict; 1 failure of our instrument; 18 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/1802.05591.json · badge: /api/ran/1802.05591.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
IrohXu/lanenet-lane-detection-pytorch community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow community (classifier label)
classifier basis not recorded on the link
3 ran · 8 no recorded run
minghanz/LaneNet community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
stesha2016/lanenet-enet-hnet community (classifier label)
classifier basis: plan_row
2 ran · 6 no recorded run
AbangLZU/lanenet-lane-detection-py2 community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
MaybeShewill-CV/lanenet-lane-detection community (classifier label)
classifier basis not recorded on the link
0 ran · 2 no recorded run
FunctionStatusWhere it lives
R_pitch Ran
ran on a synthesized input
minghanz/LaneNet/write_ipm_yml.py
code served (permissive licence) · get_code("0884d3e46f716e9e")
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 (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

def R_pitch(a):
    a = a / 180 * np.pi
    mat = np.zeros((3, 3))
    mat[0, 0] = np.cos(a)
    mat[0, 2] = np.sin(a)
    mat[1, 1] = 1
    mat[2, 0] = -np.sin(a)
    mat[2, 2] = np.cos(a)
    return mat

# The function takes a single parameter 'a' which is a scalar angle in degrees
# It divides by 180 and multiplies by pi to convert to radians
# Then uses it in trigonometric functions

ARGS = {
    "a": 45.0
}
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 (3, 3) — shape (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
R_roll Ran
ran on a synthesized input
minghanz/LaneNet/write_ipm_yml.py
code served (permissive licence) · get_code("3507ceaedfd6c2f5")
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 (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

ARGS = {
    "a": 45.0
}
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 (3, 3) — shape (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
R_yaw Ran
ran on a synthesized input
minghanz/LaneNet/write_ipm_yml.py
code served (permissive licence) · get_code("f99d82f51d3fa1b9")
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 (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

def R_yaw(a):
    a = a / 180 * np.pi
    mat = np.zeros((3, 3))
    mat[0, 0] = np.cos(a)
    mat[0, 1] = -np.sin(a)
    mat[1, 0] = np.sin(a)
    mat[1, 1] = np.cos(a)
    mat[2, 2] = 1
    return mat

# The function takes a single parameter 'a' which is a scalar angle in degrees
# It converts it to radians and constructs a 3x3 rotation matrix around the yaw axis
ARGS = {
    "a": 45.0
}
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 (3, 3) — shape (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
adjust_gamma Ran
ran on a synthesized input
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/todo_semantic_segmentation/helper.py
code served (permissive licence) · get_code("d96578a3d1da04a2")
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 (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import cv2

# Create a small sample image for testing
# The function expects a numpy array that cv2.LUT can process
# Typically this would be a grayscale or color image with uint8 values
sample_image = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)

ARGS = {
    "image": sample_image,
    "gamma": 1.2
}
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 float, shape (4, 3) — shape (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
args_str2bool Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from MaybeShewill-CV/CRNN_Tensorflow
pointer only · get_code("eba8919c2ae4a92f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

bytes_feature Ran
ran; our contract draft was wrong, not the code
AbangLZU/lanenet-lane-detection-py2/data_provider/tf_io_pipline_tools.py
code served (permissive licence) · get_code("b69809ec726c0388")
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 Feature. 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

# bytes_feature expects a 'value' parameter that should be bytes
# The function wraps it in a BytesList for TensorFlow's Feature proto

ARGS = {
    "value": b"example_bytes_data"
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
conv3x3 Ran
ran on a synthesized input
IrohXu/lanenet-lane-detection-pytorch/model/lanenet/backbone/deeplabv3_plus/resnet_atrous.py
code served (permissive licence) · get_code("fd0afd75c819b7e6")
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 Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_planes': 3,
    'out_planes': 64,
    'stride': 1,
    'atrous': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dice_coeff Ran
ran on a synthesized input
IrohXu/lanenet-lane-detection-pytorch/model/eval_function.py
code served (permissive licence) · get_code("8a2af0442a27e321")
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)

# dice_coeff expects two tensors with:
# - .size(0) method (batch dimension)
# - .view(num, -1) method (reshape to 2D)
# - element-wise multiplication
# - .sum() method

# Create two small tensors with batch size 2
# Using distinct dimensions: 2 batch, 3 channels, 4 height, 5 width
pred = torch.rand(2, 3, 4, 5)
target = torch.rand(2, 3, 4, 5)

ARGS = {
    "pred": pred,
    "target": target,
}
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
get_validation_batch Ran
ran on a synthesized input
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/datagenerator.py
code served (permissive licence) · get_code("2fd5bb4df89f9a50")
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 os
import tempfile
import numpy as np
import cv2

# Create a temporary directory structure with dummy image files
temp_dir = tempfile.mkdtemp()
images_dir = os.path.join(temp_dir, 'images')
labels_dir = os.path.join(temp_dir, 'labels')
os.makedirs(images_dir, exist_ok=True)
os.makedirs(labels_dir, exist_ok=True)

# Create dummy image files
# Create a dummy input image (BGR format for cv2)
dummy_image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
cv2.imwrite(os.path.join(images_dir, '0000.png'), dummy_image)

# Create a dummy label image
dummy_label = np.random.randint(0, 10, (100, 100, 3), dtype=np.uint8)
cv2.imwrite(os.path.join(labels_dir, '0000.png'), dummy_label)

ARGS = {
    'data_dir': temp_dir,
    'image_shape': (64, 48)
}
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 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
int64_feature Ran
ran on a synthesized input
AbangLZU/lanenet-lane-detection-py2/data_provider/tf_io_pipline_tools.py
code served (permissive licence) · get_code("f505a06000043773")
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 Feature. 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

def int64_feature(value):
    """
    
    :return:
    """
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

ARGS = {
    "value": 42
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
minmax_scale Ran
ran, honoured the contract we drafted
stesha2016/lanenet-enet-hnet/lanenet_hnet_predict.py
code served (permissive licence) · get_code("1971608da6ee2771")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family float, shape (3, 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

# Create a small numpy array with distinct values for testing minmax_scale
input_arr = np.array([[1.0, 2.0, 3.0, 4.0],
                      [5.0, 6.0, 7.0, 8.0],
                      [9.0, 10.0, 11.0, 12.0]])

ARGS = {
    'input_arr': input_arr
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 (3, 4) — shape (3, 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
resnet101_atrous Ran
ran on a synthesized input
IrohXu/lanenet-lane-detection-pytorch/model/lanenet/backbone/deeplabv3_plus/resnet_atrous.py
code served (permissive licence) · get_code("2e15559b9d73d461")
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 ResNet_Atrous. 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 = {
    'pretrained': False,
    'os': 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 ResNet_Atrous — a ResNet_Atrous output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet_Atrous 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
resnet50_atrous Ran
ran on a synthesized input
IrohXu/lanenet-lane-detection-pytorch/model/lanenet/backbone/deeplabv3_plus/resnet_atrous.py
code served (permissive licence) · get_code("05ccc649d997c21e")
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 ResNet_Atrous. 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
from torch.nn import init

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
    'os': 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 ResNet_Atrous — a ResNet_Atrous output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet_Atrous 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
spatial_dropout Ran
ran on a synthesized input
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/enet.py
code served (permissive licence) · get_code("cbb808498994f295")
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

# Create a small 4D tensor with shape [batch_size=2, height=3, width=3, channels=4]
x = tf.constant(np.random.randn(2, 3, 3, 4).astype(np.float32))

# Probability of dropping a layer
p = 0.5

# Random seed for reproducibility
seed = 42

# Scope name for the operation
scope = "spatial_dropout_test"

# Training flag
is_training = True

ARGS = {
    "x": x,
    "p": p,
    "seed": seed,
    "scope": scope,
    "is_training": is_training
}
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
spatial_dropout Ran
ran on a synthesized input
stesha2016/lanenet-enet-hnet/encoder_decoder_model/enet_stage.py
code served (permissive licence) · get_code("b3a22ff74e021b94")
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

# Create a small 4D input tensor with shape [batch_size, height, width, channels]
# Using distinct dimensions: batch=2, height=3, width=4, channels=5
x = tf.constant(np.random.randn(2, 3, 4, 5).astype(np.float32))

# Dropout probability (probability of dropping a layer)
p = 0.5

# Random seed for reproducibility
seed = 42

# Scope name for the operation
scope = "spatial_dropout_op"

# Training flag to enable/disable dropout
is_training = True

ARGS = {
    "x": x,
    "p": p,
    "seed": seed,
    "scope": scope,
    "is_training": is_training
}
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
trans_to_cuda Ran
ran, honoured the contract we drafted
IrohXu/lanenet-lane-detection-pytorch/model/lanenet/train_lanenet.py
pointer only (licence: MIT); the stored copy get_code serves, from CCIIPLab/GCE-GNN, is pointer only (licence: NONE) · get_code("7a27709bcab8b8f3")
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 CCIIPLab/GCE-GNN, 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.

cluster Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/clustering.py
code served (permissive licence) · get_code("861f83b2deb0beda")
How it ran

no invocation recorded.

discriminative_loss Not yet run
unverified (harvested, no recorded run)
AbangLZU/lanenet-lane-detection-py2/lanenet_model/lanenet_discriminative_loss.py
code served (permissive licence) · get_code("183604870fe9c8d4")
How it ran

no invocation recorded.

discriminative_loss Not yet run
unverified (harvested, no recorded run)
MaybeShewill-CV/lanenet-lane-detection/lanenet_model/lanenet_discriminative_loss.py
code served (permissive licence) · get_code("af03f9caeca5f651")
How it ran

no invocation recorded.

discriminative_loss Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/loss.py
code served (permissive licence) · get_code("75a431dc84e3aac9")
How it ran

no invocation recorded.

discriminative_loss Not yet run
unverified (harvested, no recorded run)
stesha2016/lanenet-enet-hnet/lanenet_model/lanenet_discriminative_loss.py
code served (permissive licence) · get_code("289fe15b8aee7918")
How it ran

no invocation recorded.

discriminative_loss_single Not yet run
unverified (harvested, no recorded run)
AbangLZU/lanenet-lane-detection-py2/lanenet_model/lanenet_discriminative_loss.py
code served (permissive licence) · get_code("00dec105fe4f01ce")
How it ran

no invocation recorded.

discriminative_loss_single Not yet run
unverified (harvested, no recorded run)
MaybeShewill-CV/lanenet-lane-detection/lanenet_model/lanenet_discriminative_loss.py
code served (permissive licence) · get_code("0081d5f06f6dbd99")
How it ran

no invocation recorded.

discriminative_loss_single Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/loss.py
code served (permissive licence) · get_code("18c0b3807b03817d")
How it ran

no invocation recorded.

discriminative_loss_single Not yet run
unverified (harvested, no recorded run)
stesha2016/lanenet-enet-hnet/lanenet_model/lanenet_discriminative_loss.py
code served (permissive licence) · get_code("42e6180b7b1164c2")
How it ran

no invocation recorded.

evaluate_scatter_plot Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/visualization.py
code served (permissive licence) · get_code("310ed38742c662ef")
How it ran

no invocation recorded.

get_instance_masks Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/clustering.py
code served (permissive licence) · get_code("b2e60779cf4284a6")
How it ran

no invocation recorded.

get_trainable_variables_and_initialize Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/utils.py
code served (permissive licence) · get_code("c56423bdcf53292c")
How it ran

no invocation recorded.

hnet_loss Not yet run
unverified (harvested, no recorded run)
stesha2016/lanenet-enet-hnet/lanenet_model/hnet_loss.py
code served (permissive licence) · get_code("c22d888dbcf4b272")
How it ran

no invocation recorded.

hnet_transformation Not yet run
unverified (harvested, no recorded run)
stesha2016/lanenet-enet-hnet/lanenet_model/hnet_loss.py
code served (permissive licence) · get_code("6e8cae7f5bf90dac")
How it ran

no invocation recorded.

prelu Not yet run
unverified (harvested, no recorded run)
stesha2016/lanenet-enet-hnet/encoder_decoder_model/enet_stage.py
code served (permissive licence) · get_code("748bfd352080d1ca")
How it ran

no invocation recorded.

save_instance_masks Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/clustering.py
code served (permissive licence) · get_code("2016683bf4251f65")
How it ran

no invocation recorded.

unpool Not yet run
unverified (harvested, no recorded run)
hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow/enet.py
code served (permissive licence) · get_code("a53416ca000946a2")
How it ran

no invocation recorded.

unpool Not yet run
unverified (harvested, no recorded run)
stesha2016/lanenet-enet-hnet/encoder_decoder_model/enet_stage.py
code served (permissive licence) · get_code("cc97231448e8fa54")
How it ran

no invocation recorded.

Also present in other papers' code

Of 34 samples lifted from this paper's linked repositories, 34 carry a function identity and 0 do not. Of the 29 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 20 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
bytes_feature 8 other papers
3 dated earlier, 5 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization
1609.05158 (2016-09)
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
and 5 more not named here
int64_feature 7 other papers
2 dated earlier, 5 later
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization
1611.07810 (2016-11)
A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering
1803.10562 (2018-03)
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
and 4 more not named here
trans_to_cuda 6 other papers
6 later
2005.02844 (2020-05)
TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation
2012.06852 (2020-12)
Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation
2106.05081 (2021-06)
Global Context Enhanced Graph Neural Networks for Session-based Recommendation
and 3 more not named here
args_str2bool 2 other papers
1 dated earlier, 1 later
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
2004.02147 (2020-04)
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
get_instance_masks 1 other paper
1 later
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
minmax_scale 1 other paper
1 dated earlier
1711.10098 (2017-11)
Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
save_instance_masks 1 other paper
1 later
aaai_6994 (2020 (year only))
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
spatial_dropout 1 other paper
1 dated earlier
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
unpool 1 other paper
1 dated earlier
1606.02147 (2016-06)
ENet: A Deep Neural Network Architecture for Real-Time Semantic 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

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane departure or trajectory planning decision in fully autonomous cars. Traditional lane detection methods rely on a combination of highly-specialized, hand-crafted features and heuristics, usually followed by post-processing techniques, that are computationally expensive and prone to scalability due to road scene variations. More recent approaches leverage deep learning models, trained for pixel-wise lane segmentation, even when no markings are present in the image due to their big receptive field. Despite their advantages, these methods are limited to detecting a pre-defined, fixed number of lanes, e.g. ego-lanes, and can not cope with lane changes. In this paper, we go beyond the aforementioned limitations and propose to cast the lane detection problem as an instance segmentation problem - in which each lane forms its own instance - that can be trained end-to-end. To parametrize the segmented lane instances before fitting the lane, we further propose to apply a learned perspective transformation, conditioned on the image, in contrast to a fixed "bird's-eye view" transformation. By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation. In summary, we propose a fast lane detection algorithm, running at 50 fps, which can handle a variable number of lanes and cope with lane changes. We verify our method on the tuSimple dataset and achieve competitive results.

For agents

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

get_harvested_code_for_paper("1802.05591")
get_code_for_paper("1802.05591")
have("1802.05591")

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

curl https://syntology.ai/api/ran/1802.05591.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.05591.svg)](https://syntology.ai/paper/1802.05591)

Connect an agent — have() is free.