SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.04193 · 2020

Deep Learning for Person Re-identification: A Survey and Outlook

arXiv · PDF · Open in the Atlas

Code that ran

19 of 22 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; 1 honoured the contract we drafted, 2 violated it and 9 have no contract verdict; 7 failures of our instrument; 3 no recorded run), measured 2026-11-20; 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/2001.04193.json · badge: /api/ran/2001.04193.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
zion-king/Deep-Learning-for-Person-Re-identification community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
Haoyu1004/AGW_mindspore community (classifier label)
classifier basis not recorded on the link
9 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 2 no recorded run
FunctionStatusWhere it lives
check_isfile Ran
ran, violated the contract we drafted
zion-king/Deep-Learning-for-Person-Re-identification/utils/iotools.py
code served (permissive licence) · get_code("7817df1615c1662c")
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 os.path as osp
import tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_file = osp.join(temp_dir, "test_file.txt")
with open(temp_file, "w") as f:
    f.write("test content")

ARGS = {
    "path": temp_file
}
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 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
zion-king/Deep-Learning-for-Person-Re-identification/modeling/backbones/resnet.py
code served (permissive licence) · get_code("dd1114865f06f0fd")
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 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
euclidean_dist Ran
ran; our contract draft was wrong, not the code
zion-king/Deep-Learning-for-Person-Re-identification/modeling/layer/triplet_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from needylove/regression_tightness, is pointer only (licence: NONE) · get_code("c83d9f7fca950b77")
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 needylove/regression_tightness, 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.

eval_cuhk03 Ran
ran on a synthesized input
Haoyu1004/AGW_mindspore/src/metrics/rank.py
code served (permissive licence) · get_code("ce5528b90aee9251")
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 numpy as np

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

# Create small test data
num_q = 2  # number of query samples
num_g = 4  # number of gallery samples
max_rank = 3

# Create a distance matrix (num_q x num_g)
# Smaller values = better matches
distmat = np.array([
    [0.1, 0.5, 0.3, 0.8],
    [0.2, 0.6, 0.1, 0.7]
], dtype=np.float32)

# Query person IDs
q_pids = np.array([0, 1], dtype=np.int32)

# Gallery person IDs
# Include matches for at least some queries to avoid the assertion error
g_pids = np.array([0, 1, 2, 0], dtype=np.int32)

# Query camera IDs
q_camids = np.array([0, 1], dtype=np.int32)

# Gallery camera IDs
# Make sure some gallery samples have different camera IDs than queries
# to ensure the remove mask works correctly
g_camids = np.array([1, 0, 0, 0], dtype=np.int32)

ARGS = {
    'distmat': distmat,
    'q_pids': q_pids,
    'g_pids': g_pids,
    'q_camids': q_camids,
    'g_camids': g_camids,
    'max_rank': max_rank
}
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 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
eval_market1501 Ran
ran on a synthesized input
Haoyu1004/AGW_mindspore/src/metrics/rank.py
code served (permissive licence) · get_code("ee2fbb15866cc877")
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 numpy as np

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

# Create a small distance matrix (num_queries=3, num_gallery=5)
# Each entry is a distance score (smaller = more similar)
distmat = np.array([
    [0.1, 0.2, 0.3, 0.5, 0.8],
    [0.2, 0.1, 0.4, 0.6, 0.9],
    [0.3, 0.4, 0.1, 0.7, 1.0]
], dtype=np.float32)

# Query person IDs (3 queries)
q_pids = np.array([0, 1, 2], dtype=np.int32)

# Gallery person IDs (5 gallery images)
g_pids = np.array([0, 1, 0, 2, 1], dtype=np.int32)

# Query camera IDs (3 queries)
q_camids = np.array([0, 1, 0], dtype=np.int32)

# Gallery camera IDs (5 gallery images)
g_camids = np.array([0, 1, 1, 0, 2], dtype=np.int32)

# Maximum rank to evaluate
max_rank = 5

ARGS = {
    'distmat': distmat,
    'q_pids': q_pids,
    'g_pids': g_pids,
    'q_camids': q_camids,
    'g_camids': g_camids,
    'max_rank': max_rank
}
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 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
evaluate_py Ran
ran on a synthesized input
Haoyu1004/AGW_mindspore/src/metrics/rank.py
code served (permissive licence) · get_code("ecbd84f325abbab0")
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 numpy as np

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

# Create small distance matrix: 2 queries x 3 gallery samples
num_queries = 2
num_gallery = 3
distmat = np.random.rand(num_queries, num_gallery).astype(np.float32)

# Query person IDs: 2 queries
q_pids = np.array([0, 1], dtype=np.int32)

# Gallery person IDs: 3 gallery samples
g_pids = np.array([0, 1, 0], dtype=np.int32)

# Query camera IDs: 2 queries
q_camids = np.array([0, 1], dtype=np.int32)

# Gallery camera IDs: 3 gallery samples (at least one must differ from query camera to have valid matches)
g_camids = np.array([1, 0, 0], dtype=np.int32)

# Max rank for evaluation
max_rank = 2

# Whether to use CUHK03 metric
use_metric_cuhk03 = False

ARGS = {
    'distmat': distmat,
    'q_pids': q_pids,
    'g_pids': g_pids,
    'q_camids': q_camids,
    'g_camids': g_camids,
    'max_rank': max_rank,
    'use_metric_cuhk03': use_metric_cuhk03
}
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 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
hard_example_mining Ran
ran on a synthesized input
zion-king/Deep-Learning-for-Person-Re-identification/modeling/layer/triplet_loss.py
code served (permissive licence) · get_code("93f2c0b80ea7f36e")
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 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a distance matrix of shape [N, N]
# N = 4 samples
N = 4
dist_mat = torch.randn(N, N)
dist_mat = torch.abs(dist_mat)  # Make distances positive

# Create labels - we need samples grouped by class
# For hard example mining to work properly, we need multiple samples per class
# Let's have 2 classes with 2 samples each
labels = torch.LongTensor([0, 0, 1, 1])

ARGS = {
    "dist_mat": dist_mat,
    "labels": labels,
    "return_inds": 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 tuple, ndim 2, 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
linear_warmup_lr Ran
ran, honoured the contract we drafted
Haoyu1004/AGW_mindspore/src/utils/lr_generator.py
code served (permissive licence) · get_code("56d39004d57cb3a2")
How it ran

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

import torch
import numpy as np

# Analyze the function:
# - current_step: int, used in arithmetic
# - warmup_steps: int/float, used in division
# - base_lr: float, used in arithmetic
# - init_lr: float, used in arithmetic

ARGS = {
    "current_step": 500,
    "warmup_steps": 1000,
    "base_lr": 0.1,
    "init_lr": 0.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge Ran
ran; our contract draft was wrong, not the code
Haoyu1004/AGW_mindspore/src/utils/config.py
code served (permissive licence) · get_code("b9e24c3e3e0e88a7")
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 argparse

torch.manual_seed(0)

# Create a mock args object with some attributes
args = argparse.Namespace(
    learning_rate=0.001,
    batch_size=32,
    epochs=10,
    model_name="test_model",
    debug=True,
    seed=42
)

# Create a base configuration dictionary
cfg = {
    "default_lr": 0.0001,
    "default_batch": 16,
    "dataset": "cifar10"
}

ARGS = {
    "args": args,
    "cfg": cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
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
normalize Ran
ran; our contract draft was wrong, not the code
zion-king/Deep-Learning-for-Person-Re-identification/modeling/layer/triplet_loss.py
code served (permissive licence) · get_code("e3b2a83f52101f2d")
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 tensor with batch size 2 and feature dimension 4
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "axis": -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 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
parse_cli_to_yaml Ran
ran; our contract draft was wrong, not the code
Haoyu1004/AGW_mindspore/src/utils/config.py
code served (permissive licence) · get_code("ff75f4d130ead571")
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 Namespace. 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 argparse
import ast

# Create a minimal parent parser
parent_parser = argparse.ArgumentParser(add_help=False)

# Create a base configuration dictionary with various types
cfg = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 100,
    'use_cuda': False,
    'model_name': 'resnet50',
    'dropout_rate': 0.5,
    'layer_sizes': [128, 256, 512],
    'optimizer_names': ['adam', 'sgd'],
}

# Create helper descriptions
helper = {
    'learning_rate': 'Learning rate for optimization',
    'batch_size': 'Batch size for training',
    'epochs': 'Number of training epochs',
    'use_cuda': 'Whether to use CUDA',
    'model_name': 'Name of the model architecture',
    'dropout_rate': 'Dropout rate for regularization',
    'layer_sizes': 'Sizes of hidden layers',
    'optimizer_names': 'Names of optimizers to try',
}

# Create choices for certain parameters
choices = {
    'model_name': ['resnet50', 'vgg16', 'inception'],
    'optimizer_names': ['adam', 'sgd', 'rmsprop'],
}

# Define the path to the default config
cfg_path = 'default_config.yaml'

ARGS = {
    'parser': parent_parser,
    'cfg': cfg,
    'helper': helper,
    'choices': choices,
    'cfg_path': cfg_path,
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
parse_yaml Ran
ran; our contract draft was wrong, not the code
Haoyu1004/AGW_mindspore/src/utils/config.py
code served (permissive licence) · get_code("8486896224aa5191")
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 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 tempfile
import os
import yaml

# Create a temporary YAML file with valid config structure
temp_dir = tempfile.mkdtemp()
yaml_path = os.path.join(temp_dir, "config.yaml")

# Write a valid YAML file with 3 documents (config, helper, choices)
yaml_content = """
model: resnet50
learning_rate: 0.001
batch_size: 32
---
model: "Type of model to use"
learning_rate: "Learning rate for optimizer"
batch_size: "Batch size for training"
---
model: ["resnet50", "vgg16", "mobilenet"]
learning_rate: [0.0001, 0.001, 0.01]
batch_size: [16, 32, 64]
"""

with open(yaml_path, 'w', encoding='utf-8') as f:
    f.write(yaml_content)

ARGS = {
    "yaml_path": yaml_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
yaml — 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
read_json Ran
ran; our contract draft was wrong, not the code
zion-king/Deep-Learning-for-Person-Re-identification/utils/iotools.py
pointer only (licence: MIT); the stored copy get_code serves, from luomingshuang/M3GPT, is pointer only (licence: NONE) · get_code("7d6e263caea8e963")
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 luomingshuang/M3GPT, 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.

resnet101_ibn_a Ran
ran on a synthesized input
zion-king/Deep-Learning-for-Person-Re-identification/modeling/backbones/resnet_ibn_a.py
code served (permissive licence) · get_code("f3a89c60b7c760a9")
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_IBN. 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 = {
    'last_stride': 1,
    'pretrained': False,
}
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_IBN — a ResNet_IBN output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet_IBN 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
resnet152_ibn_a Ran
ran on a synthesized input
zion-king/Deep-Learning-for-Person-Re-identification/modeling/backbones/resnet_ibn_a.py
code served (permissive licence) · get_code("295f89c9a58b123e")
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_IBN. 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 = {
    'last_stride': 1,
    'pretrained': False,
}
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_IBN — a ResNet_IBN output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet_IBN 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
setup_logger Ran
ran on a synthesized input
zion-king/Deep-Learning-for-Person-Re-identification/utils/logger.py
code served (permissive licence) · get_code("d5b4cd03446719f9")
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 Logger. 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 logging
import os
import sys
import tempfile

# Create a temporary directory for logging
temp_dir = tempfile.mkdtemp()

ARGS = {
    "name": "test_logger",
    "save_dir": temp_dir,
    "distributed_rank": 0
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
str2bool Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from sajadn/Exemplar-VAE
pointer only · get_code("7c508037b40522af")
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.

warmup_step_lr Ran
ran on a synthesized input
Haoyu1004/AGW_mindspore/src/utils/lr_generator.py
code served (permissive licence) · get_code("c69ee6acc82be011")
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 (1000,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from collections import Counter

def linear_warmup_lr(current_step, warmup_steps, base_lr, init_lr):
    """Linear learning rate."""
    lr_inc = (float(base_lr) - float(init_lr)) / float(warmup_steps)
    lr = float(init_lr) + lr_inc * current_step
    return lr

def warmup_step_lr(base_lr, lr_epochs, steps_per_epoch, warmup_epochs, max_epoch, gamma=0.1):
    """Warmup step learning rate.
       This warmup warmups lr by *EPOCHS*
    """
    lr_each_epoch = []
    milestones_steps_counter = Counter(lr_epochs)
    lr = float(base_lr)
    for i in range(max_epoch):
        if i < warmup_epochs:
            lr = linear_warmup_lr(i + 1, warmup_epochs, base_lr, 0)
        else:
            lr = lr * gamma ** milestones_steps_counter[i]
        lr_each_epoch.append(lr)
    lr_each_step = []
    for epoch_lr in lr_each_epoch:
        lr_each_step += [epoch_lr] * steps_per_epoch
    return np.array(lr_each_step).astype(np.float32)

ARGS = {
    "base_lr": 0.1,
    "lr_epochs": [3, 5, 7],
    "steps_per_epoch": 100,
    "warmup_epochs": 2,
    "max_epoch": 10,
    "gamma": 0.1
}
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 1, dtype family float, shape (1000,) — shape (1000,) 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
warmup_step_lr_1 Ran
ran on a synthesized input
Haoyu1004/AGW_mindspore/src/utils/lr_generator.py
code served (permissive licence) · get_code("1c995b3e930c8f8e")
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 (10000,) 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 = {
    "lr": 0.1,
    "lr_epochs": [30, 60],
    "steps_per_epoch": 100,
    "warmup_epochs": 5,
    "max_epoch": 100,
    "gamma": 0.1,
}
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 1, dtype family float, shape (10000,) — shape (10000,) 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
compute_mAP Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from wtyhub/MuseNet
pointer only · get_code("3f91b09177ddeb33")
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. No invocation recorded.

evaluate Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from jiangsikai/Person_reID_baseline_pytorch
pointer only · get_code("3713e246e333c32a")
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. No invocation recorded.

resnet50_ibn_a Not yet run
unverified (harvested, no recorded run)
zion-king/Deep-Learning-for-Person-Re-identification/modeling/backbones/resnet_ibn_a.py
code served (permissive licence) · get_code("4008920c34a176e9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 13 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 3 the same month, 10 later) and 9 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
conv3x3 686 other papers
182 dated earlier, 4 the same month, 499 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
str2bool 175 other papers
11 dated earlier, 1 the same month, 163 later · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
normalize 29 other papers
7 dated earlier, 22 later
1609.01775 (2016-09)
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
1811.07130 (2018-11)
Batch DropBlock Network for Person Re-identification and Beyond
and 26 more not named here
merge 28 other papers
17 dated earlier, 11 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
and 25 more not named here
euclidean_dist 20 other papers
4 dated earlier, 1 the same month, 15 later · 4 only as an assembly brick
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1903.07071 (2019-03)
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
1904.02998 (2019-04)
Relation-Aware Global Attention for Person Re-identification
and 17 more not named here
linear_warmup_lr 8 other papers
4 dated earlier, 4 later
1611.06612 (2016-11)
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
and 5 more not named here
read_json 8 other papers
2 dated earlier, 6 later
1612.05601 (2016-12)
SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound
1903.11306 (2019-03)
Linkage Based Face Clustering via Graph Convolution Network
2104.06770 (2021-04)
Graph-based Person Signature for Person Re-Identifications
and 5 more not named here
compute_mAP 7 other papers
3 dated earlier, 4 later
1711.10295 (2017-11)
Camera Style Adaptation for Person Re-identification
1812.03282 (2018-12)
Spatial-Temporal Person Re-identification
1904.07223 (2019-04)
Joint Discriminative and Generative Learning for Person Re-identification
and 4 more not named here
hard_example_mining 7 other papers
3 dated earlier, 4 later
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
1903.07071 (2019-03)
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
1904.07223 (2019-04)
Joint Discriminative and Generative Learning for Person Re-identification
and 4 more not named here
evaluate 2 other papers
2 dated earlier
1711.10295 (2017-11)
Camera Style Adaptation for Person Re-identification
1904.07223 (2019-04)
Joint Discriminative and Generative Learning for Person Re-identification
check_isfile 1 other paper
1 later
2104.06770 (2021-04)
Graph-based Person Signature for Person Re-Identifications
parse_cli_to_yaml 1 other paper
1 dated earlier
1910.06827 (2019-10)
Learning Generalisable Omni-Scale Representations for Person Re-Identification
parse_yaml 1 other paper
1 dated earlier
1910.06827 (2019-10)
Learning Generalisable Omni-Scale Representations for Person Re-Identification

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 2026-11-20.

Repositories linked to this paper

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

Abstract

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on twelve datasets for FOUR different Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for real applications. Finally, some important yet under-investigated open issues are discussed.

For agents

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

get_harvested_code_for_paper("2001.04193")
get_code_for_paper("2001.04193")
have("2001.04193")

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

curl https://syntology.ai/api/ran/2001.04193.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.04193.svg)](https://syntology.ai/paper/2001.04193)

Connect an agent — have() is free.