SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1606.02147 · 2016

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

26 of 30 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; 3 honoured the contract we drafted, 0 violated it and 19 have no contract verdict; 4 failures of our instrument; 4 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/1606.02147.json · badge: /api/ran/1606.02147.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
alililia/ascend_E-NET community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
Shun14/enet community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
xiaoyufenfei/LEDNet community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
iArunava/ENet-Real-Time-Semantic-Segmentation community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
adrshm91/segmentationEnet community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
davidtvs/PyTorch-ENet community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
kwotsin/TensorFlow-ENet community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
fregu856/segmentation community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
batch_transform Ran
ran on a synthesized input
davidtvs/PyTorch-ENet/utils.py
code served (permissive licence) · get_code("599debf6e1c7afb4")
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 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create a small batch of tensors
# batch_transform uses torch.unbind(batch) which unbinds along dimension 0
# So batch should be a tensor where dim 0 is the batch dimension
batch = torch.randn(2, 4)  # batch size 2, feature dim 4

# Define a simple transform function
# The transform is called on each individual tensor from torch.unbind(batch)
# torch.unbind(batch) returns a list of 1D tensors of shape (4,)
# So transform should take a 1D tensor and return a tensor
def transform(tensor):
    """Simple transform that scales a tensor"""
    return tensor * 2.0

ARGS = {
    "batch": batch,
    "transform": transform,
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
channel_shuffle Ran
ran; our contract draft was wrong, not the code
xiaoyufenfei/LEDNet/imagenet-pretrain/lednet_imagenet.py
pointer only (licence: MIT); the stored copy get_code serves, from ddghost/new_darts, is pointer only (licence: NONE) · get_code("b9da06d4f527dd6c")
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 ddghost/new_darts, 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.

colormap Ran
ran, honoured the contract we drafted
xiaoyufenfei/LEDNet/utils/transform.py
pointer only (licence: MIT); the stored copy get_code serves, from CVRL/OpenSourceIrisRecognition, is pointer only (licence: NONE) · get_code("eb024d61772489c9")
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 CVRL/OpenSourceIrisRecognition, 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.

colormap_cityscapes Ran
ran on a synthesized input
xiaoyufenfei/LEDNet/utils/transform.py
code served (permissive licence) · get_code("99041b5a06df43ad")
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 (20, 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 = {
    "n": 20
}
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 int, shape (20, 3) — shape (20, 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
create_class_mask Ran
ran on a synthesized input
iArunava/ENet-Real-Time-Semantic-Segmentation/utils.py
code served (permissive licence) · get_code("6ed362b4f0b5f5f1")
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 (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 segmented image with shape (height, width, channels)
# Using normalized values (0-1 range)
img = np.random.rand(4, 5, 3).astype(np.float32)
# Normalize to 0-1 range
img = img / 255.0

# Create a color map with a few distinct RGB colors
# These are normalized (0-1 range)
color_map = [
    (0.0, 0.0, 0.0),      # Black
    (1.0, 0.0, 0.0),      # Red
    (0.0, 1.0, 0.0),      # Green
]

ARGS = {
    "img": img,
    "color_map": color_map,
    "is_normalized_img": True,
    "is_normalized_map": True,
    "show_masks": False,
}
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 int, 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
decode_segmap Ran
ran on a synthesized input
iArunava/ENet-Real-Time-Semantic-Segmentation/utils.py
code served (permissive licence) · get_code("9c590e1757837710")
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 (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

# The function takes a segmentation map (image) where each pixel value is a label index
# and converts it to an RGB image using a color palette.
# The image should be a 2D numpy array with integer label values (0-11 for the 12 classes)

# Create a simple segmentation map with shape (4, 3) containing label indices
segmentation_map = np.array([
    [0, 1, 2],
    [3, 4, 5],
    [6, 7, 8],
    [9, 10, 11]
], dtype=np.int32)

ARGS = {
    "image": segmentation_map
}
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 int, 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
flip_combination Ran
ran on a synthesized input
Shun14/enet/paddleseg/core/infer.py
code served (permissive licence) · get_code("95bccf5957a196e4")
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.

# Setup code for flip_combination function

ARGS = {
    "flip_horizontal": False,
    "flip_vertical": False,
}
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 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
getBool Ran
ran on a synthesized input
alililia/ascend_E-NET/src/util.py
code served (permissive licence) · get_code("0be453fd7e80102c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

def getBool(string):
    """from str to bool"""
    if string == 'true':
        b = True
    elif string == 'false':
        b = False
    else:
        raise RuntimeError('string should be "true" or "false"')
    return b


ARGS = {
    'string': 'true'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
getColorEntry Ran
ran on a synthesized input
xiaoyufenfei/LEDNet/utils/iouEval.py
code served (permissive licence) · get_code("d40f8d453fe5f80c")
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 str. 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

ARGS = {
    "val": 0.5
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_class_weights Ran
ran on a synthesized input
iArunava/ENet-Real-Time-Semantic-Segmentation/utils.py
code served (permissive licence) · get_code("f7071fb80d60a088")
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 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create temporary mock loader that yields (inputs, labels)
class MockLoader:
    def __init__(self, batch_size=2, num_classes=5):
        self.batch_size = batch_size
        self.num_classes = num_classes
    
    def __next__(self):
        # Create mock inputs: (batch_size, channels, height, width)
        inputs = torch.randn(self.batch_size, 3, 4, 4)
        
        # Create mock labels: (batch_size, height, width) with class indices
        labels = torch.randint(0, self.num_classes, (self.batch_size, 4, 4))
        
        return (inputs, labels)
    
    def __iter__(self):
        return self

mock_loader = MockLoader(batch_size=2, num_classes=5)

ARGS = {
    "loader": mock_loader,
    "num_classes": 5,
    "c": 1.02
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, matplotlib, 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 1, dtype family float, shape (5,) — shape (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
get_image_list Ran
ran on a synthesized input
Shun14/enet/predict.py
code served (permissive licence) · get_code("c8f710d7401e0006")
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 shutil

# Create a temporary directory with test images
temp_dir = tempfile.mkdtemp()

# Create a few test image files
test_image_path1 = os.path.join(temp_dir, "image1.jpg")
test_image_path2 = os.path.join(temp_dir, "image2.png")
with open(test_image_path1, 'w') as f:
    f.write("dummy image content")
with open(test_image_path2, 'w') as f:
    f.write("dummy image content")

# Test with directory path
image_path_dir = temp_dir

ARGS = {
    "image_path": image_path_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 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
get_reverse_list Ran
ran on a synthesized input
Shun14/enet/paddleseg/core/infer.py
code served (permissive licence) · get_code("026fee631ce4a66c")
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. 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 numpy as np


class Resize:
    def __init__(self, target_size):
        self.target_size = target_size


class ResizeByLong:
    def __init__(self, long_size):
        self.long_size = long_size


class Padding:
    def __init__(self, target_size):
        self.target_size = target_size


class PaddingByAspectRatio:
    def __init__(self, aspect_ratio):
        self.aspect_ratio = aspect_ratio


class LimitLong:
    def __init__(self, max_long=None, min_long=None):
        self.max_long = max_long
        self.min_long = min_long


ARGS = {
    "ori_shape": [480, 640],
    "transforms": [
        Resize((256, 256)),
        ResizeByLong(512),
        Padding((512, 512)),
        PaddingByAspectRatio(1.5),
        LimitLong(max_long=1024, min_long=256),
    ]
}
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 list — a list 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
get_test_config Ran
ran; our contract draft was wrong, not the code
Shun14/enet/val.py
code served (permissive licence) · get_code("20eb3e6b0aba73e4")
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 dict. 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 numpy as np

class SimpleArgs:
    def __init__(self):
        self.aug_eval = True
        self.scales = [0.5, 1.0, 1.5]
        self.flip_horizontal = True
        self.flip_vertical = False
        self.is_slide = True
        self.crop_size = 512
        self.stride = 256

class SimpleConfig:
    def __init__(self):
        self.test_config = {
            'aug_eval': False,
            'scales': [1.0],
            'flip_horizontal': False,
            'flip_vertical': False,
            'is_slide': False,
            'crop_size': 256,
            'stride': 128
        }

cfg = SimpleConfig()
args = SimpleArgs()

ARGS = {
    'cfg': cfg,
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_test_config Ran
ran on a synthesized input
Shun14/enet/predict.py
code served (permissive licence) · get_code("32d2a7cc8725e25e")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Stand-in class for cfg parameter
class Config:
    def __init__(self):
        self.test_config = {
            'model': 'resnet50',
            'batch_size': 8,
            'num_workers': 4
        }

# Stand-in class for args parameter
class Args:
    def __init__(self):
        self.aug_pred = True
        self.scales = [0.5, 1.0, 1.5]
        self.flip_horizontal = True
        self.flip_vertical = False
        self.is_slide = True
        self.crop_size = 512
        self.stride = 256

ARGS = {
    'cfg': Config(),
    'args': Args()
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
is_image Ran
ran on a synthesized input
alililia/ascend_E-NET/src/dataset.py
code served (permissive licence) · get_code("48024d1a7659869b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    'filename': 'image.jpg'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_label Ran
ran on a synthesized input
alililia/ascend_E-NET/src/eval310.py
code served (permissive licence) · get_code("8021631fe7e194d3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "filename": "image_labelTrainIds.png"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_checkpoint Ran
ran on a synthesized input
davidtvs/PyTorch-ENet/utils.py
code served (permissive licence) · get_code("59005d1e1e0f3e6f")
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 torch
import torch.nn as nn
import os
import tempfile

torch.manual_seed(0)

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

# Create model and optimizer instances
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a temporary directory and save a checkpoint
temp_dir = tempfile.mkdtemp()
filename = "checkpoint.pth"
model_path = os.path.join(temp_dir, filename)

# Create and save a checkpoint with the required structure
checkpoint = {
    'state_dict': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'epoch': 42,
    'miou': 0.85
}
torch.save(checkpoint, model_path)

# Create fresh model and optimizer instances for loading
model_for_loading = SimpleModel()
optimizer_for_loading = torch.optim.SGD(model_for_loading.parameters(), lr=0.01)

ARGS = {
    'model': model_for_loading,
    'optimizer': optimizer_for_loading,
    'folder_dir': temp_dir,
    'filename': filename
}
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
load_image Ran
ran, honoured the contract we drafted
alililia/ascend_E-NET/src/eval310.py
code served (permissive licence) · get_code("1c803ce4388e0644")
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 PngImageFile. 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 io
from PIL import Image

# Create a small in-memory image file
img = Image.new('RGB', (10, 10), color='red')
img_bytes = io.BytesIO()
img.save(img_bytes, format='PNG')
img_bytes.seek(0)

ARGS = {
    'file': img_bytes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_image Ran
ran, honoured the contract we drafted
alililia/ascend_E-NET/src/dataset.py
code served (permissive licence) · get_code("127533b21bcc84b5")
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 PngImageFile. 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 io
import torch
from PIL import Image
import numpy as np

# Create a small test image in memory
img_array = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)
img = Image.fromarray(img_array)

# Save to a BytesIO object (in-memory file)
file_obj = io.BytesIO()
img.save(file_obj, format='PNG')
file_obj.seek(0)

ARGS = {
    'file': file_obj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
max_unpool Ran
ran on a synthesized input
adrshm91/segmentationEnet/utilities.py
code served (permissive licence) · get_code("c9f38b5c4a775ebd")
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 4, 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 tensorflow as tf
import numpy as np

# Create small valid inputs for max_unpool
batch_size = 2
height_pooled = 2
width_pooled = 2
channels = 4

# Output shape: [batch, height_original, width_original, channels]
output_shape = [batch_size, 4, 4, channels]

# Create small input tensor (pooled feature maps)
inputs = tf.constant(np.random.randn(batch_size, height_pooled, width_pooled, channels).astype(np.float32))

# Create pooling indices tensor (same shape as inputs, containing flat indices into output)
# Values should be valid indices in the flattened output space
pooling_indices = tf.constant(
    np.array([
        [[0, 1, 4, 5], [8, 9, 12, 13], [16, 17, 20, 21], [24, 25, 28, 29]],
        [[32, 33, 36, 37], [40, 41, 44, 45], [48, 49, 52, 53], [56, 57, 60, 61]]
    ]).reshape(batch_size, height_pooled, width_pooled, channels),
    dtype=tf.int64
)

k_size = [1, 2, 2, 1]

ARGS = {
    "inputs": inputs,
    "pooling_indices": pooling_indices,
    "output_shape": output_shape,
    "k_size": k_size
}
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 EagerTensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py recorded SymbolicTensor ndim 4, 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
max_unpool Ran
ran on a synthesized input
fregu856/segmentation/utilities.py
code served (permissive licence) · get_code("72d70919eb58cc17")
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 4, dtype family float, shape (2, 4, 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 tensorflow as tf
import numpy as np

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

# Create small tensors for testing
batch_size = 2
height_pooled = 2
width_pooled = 2
channels = 4

# Output shape after unpooling (batch, height, width, channels)
output_shape = [batch_size, 4, 4, channels]

# Create input tensor (pooled feature maps)
# Shape: [batch_size, height_pooled, width_pooled, channels]
inputs = tf.constant(
    np.random.randn(batch_size, height_pooled, width_pooled, channels).astype(np.float32)
)

# Create pooling indices tensor
# These indices represent where each pooled value came from in the unpooled feature map
# Shape: [batch_size, height_pooled, width_pooled, channels]
# Values should be in range [0, output_height * output_width)
pooling_indices = tf.constant(
    np.random.randint(0, output_shape[1] * output_shape[2], 
                      size=(batch_size, height_pooled, width_pooled, channels)),
    dtype=tf.int32
)

# k_size parameter (kernel size for pooling)
k_size = [1, 2, 2, 1]

# Construct the ARGS dictionary
ARGS = {
    "inputs": inputs,
    "pooling_indices": pooling_indices,
    "output_shape": output_shape,
    "k_size": k_size
}
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 EagerTensor, ndim 4, dtype family float, shape (2, 4, 4, 4) — shape (2, 4, 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
partition_list Ran
ran; our contract draft was wrong, not the code
Shun14/enet/paddleseg/core/predict.py
code served (permissive licence) · get_code("2f75a098ce9f7b0e")
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 list. 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 math

def partition_list(arr, m):
    """split the list 'arr' into m pieces"""
    n = int(math.ceil(len(arr) / float(m)))
    return [arr[i:i + n] for i in range(0, len(arr), n)]

# Setup code
arr = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
m = 3

ARGS = {
    "arr": arr,
    "m": m
}
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 list — a list 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
resize Ran
ran on a synthesized input
alililia/ascend_E-NET/src/dataset.py
code served (permissive licence) · get_code("5d56ce0fb9020da6")
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 Image. 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.

from PIL import Image
import torch

torch.manual_seed(0)

# Create a small PIL Image for testing
# The function expects img to have a .size attribute (width, height)
# and a .resize method that takes (size, interpolation) and returns a resized image
img = Image.new('RGB', (100, 50))  # width=100, height=50

# height parameter - an integer
height = 25

# interpolation parameter - a PIL Image resampling filter
interpolation = Image.LANCZOS

ARGS = {
    'img': img,
    'height': height,
    'interpolation': interpolation
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
spatial_dropout Ran
ran on a synthesized input
kwotsin/TensorFlow-ENet/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
adrshm91/segmentationEnet/utilities.py
code served (permissive licence) · get_code("10706543dfcc19b0")
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 4, dtype family float, shape (2, 3, 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 tensorflow as tf

# Create a small 4D tensor suitable for spatial dropout
# Shape: [batch_size=2, height=3, width=3, channels=4]
x = tf.random.normal(shape=[2, 3, 3, 4])

# Dropout probability
drop_prob = 0.5

ARGS = {
    "x": x,
    "drop_prob": drop_prob,
}
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 4, dtype family float, shape (2, 3, 3, 4) — shape (2, 3, 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
split Ran
ran; our contract draft was wrong, not the code
xiaoyufenfei/LEDNet/imagenet-pretrain/lednet_imagenet.py
code served (permissive licence) · get_code("8f2448483b5d9342")
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 5, 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

torch.manual_seed(0)

# The function takes a 4D tensor x and splits it along dimension 1 (channels)
# It expects x to have shape (batch, channels, height, width)
# Let's create a small tensor with distinct dimensions for clarity

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

ARGS = {
    "x": x
}
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 5, 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
PReLU Not yet run
unverified (harvested, no recorded run)
adrshm91/segmentationEnet/utilities.py
code served (permissive licence) · get_code("5c761d2d09e7ba63")
How it ran

no invocation recorded.

convert_to_one_hot Not yet run
unverified (harvested, no recorded run)
alililia/ascend_E-NET/src/iou_eval.py
code served (permissive licence) · get_code("11aacaf9af63492c")
How it ran

no invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
kwotsin/TensorFlow-ENet/preprocessing.py
code served (permissive licence) · get_code("c3e13fd4733c18c4")
How it ran

no invocation recorded.

unpool Not yet run
unverified (harvested, no recorded run)
kwotsin/TensorFlow-ENet/enet.py
code served (permissive licence) · get_code("a53416ca000946a2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 30 samples lifted from this paper's linked repositories, 30 carry a function identity and 0 do not. Of the 29 distinct functions with an identity, 14 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 13 later) and 15 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
channel_shuffle 19 other papers
1 dated earlier, 18 later · 2 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1805.12549 (2018-05)
Channel Gating Neural Networks
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
and 16 more not named here
partition_list 8 other papers
8 later
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1808.00897 (2018-08)
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
and 5 more not named here
flip_combination 7 other papers
7 later
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1808.00897 (2018-08)
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
and 4 more not named here
get_test_config 6 other papers
6 later
1803.06815 (2018-03)
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
1803.08904 (2018-03)
Context Encoding for Semantic Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
and 3 more not named here
get_reverse_list 4 other papers
4 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1811.11431 (2018-11)
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
1901.02446 (2019-01)
Panoptic Feature Pyramid Networks
and 1 more not named here
get_image_list 3 other papers
3 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1901.02446 (2019-01)
Panoptic Feature Pyramid Networks
1912.08193 (2019-12)
PointRend: Image Segmentation as Rendering
get_test_config 3 other papers
3 later
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1901.02446 (2019-01)
Panoptic Feature Pyramid Networks
1912.08193 (2019-12)
PointRend: Image Segmentation as Rendering
colormap 1 other paper
1 later
2605.20735 (2026-05)
Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition
is_image 1 other paper
1 later
1812.01803 (2018-12)
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
is_label 1 other paper
1 later
1812.01803 (2018-12)
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
load_image 1 other paper
1 later
1812.01803 (2018-12)
ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
spatial_dropout 1 other paper
1 later
1802.05591 (2018-02)
Towards End-to-End Lane Detection: an Instance Segmentation Approach
split 1 other paper
1 dated earlier
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
unpool 1 other paper
1 later
1802.05591 (2018-02)
Towards End-to-End Lane Detection: an Instance Segmentation Approach

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

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications. Recent deep neural networks aimed at this task have the disadvantage of requiring a large number of floating point operations and have long run-times that hinder their usability. In this paper, we propose a novel deep neural network architecture named ENet (efficient neural network), created specifically for tasks requiring low latency operation. ENet is up to 18$\times$ faster, requires 75$\times$ less FLOPs, has 79$\times$ less parameters, and provides similar or better accuracy to existing models. We have tested it on CamVid, Cityscapes and SUN datasets and report on comparisons with existing state-of-the-art methods, and the trade-offs between accuracy and processing time of a network. We present performance measurements of the proposed architecture on embedded systems and suggest possible software improvements that could make ENet even faster.

For agents

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

get_harvested_code_for_paper("1606.02147")
get_code_for_paper("1606.02147")
have("1606.02147")

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

curl https://syntology.ai/api/ran/1606.02147.json

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

[![Syntology run record](https://syntology.ai/api/ran/1606.02147.svg)](https://syntology.ai/paper/1606.02147)

Connect an agent — have() is free.