SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.00758 · 2017

HashNet: Deep Learning to Hash by Continuation

arXiv · PDF · Open in the Atlas

Code that ran

14 of 16 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, 0 violated it and 11 have no contract verdict; 2 failures of our instrument; 2 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/1702.00758.json · badge: /api/ran/1702.00758.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
thuml/HashNet canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
hatimwen/paddle_hashnet community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
CalcHammingDist Ran
ran on a synthesized input
hatimwen/paddle_hashnet/utils/tools.py
code served (permissive licence) · get_code("fec8bc71986e9775")
How it ran

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

# B1 and B2 are binary matrices (or any numeric matrices)
# The function computes Hamming distance using dot product
# B1 shape: (n_samples_1, q) where q is number of bits
# B2 shape: (n_samples_2, q) where q is number of bits
# Result shape: (n_samples_1, n_samples_2)

B1 = np.array([
    [1, 0, 1, 0],
    [0, 1, 1, 1]
], dtype=np.float32)

B2 = np.array([
    [1, 1, 0, 0],
    [0, 0, 1, 1],
    [1, 0, 1, 0]
], dtype=np.float32)

ARGS = {
    "B1": B1,
    "B2": B2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
CalcTopMap Ran
ran on a synthesized input
hatimwen/paddle_hashnet/utils/tools.py
code served (permissive licence) · get_code("ac4069aac5bd1718")
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 float64, ndim 0, 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 numpy as np

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

# Create small binary matrices
# rB: retrieval binary codes, shape (num_retrieval, code_length)
# qB: query binary codes, shape (num_query, code_length)
# Using code_length=4 as dimension
num_retrieval = 5
num_query = 2
code_length = 4

rB = np.random.randint(0, 2, size=(num_retrieval, code_length)).astype(np.float32)
qB = np.random.randint(0, 2, size=(num_query, code_length)).astype(np.float32)

# retrievalL: retrieval labels, shape (num_retrieval, num_classes)
# queryL: query labels, shape (num_query, num_classes)
# Using num_classes=3
num_classes = 3
retrievalL = np.random.randint(0, 2, size=(num_retrieval, num_classes)).astype(np.float32)
queryL = np.random.randint(0, 2, size=(num_query, num_classes)).astype(np.float32)

# Ensure at least some ground truth matches exist
queryL[0, 0] = 1
retrievalL[0, 0] = 1

# topk: number of top results to evaluate
topk = 3

ARGS = {
    'rB': rB,
    'qB': qB,
    'retrievalL': retrievalL,
    'queryL': queryL,
    'topk': topk
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, 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
config_dataset Ran
ran on a synthesized input
hatimwen/paddle_hashnet/utils/datasets.py
code served (permissive licence) · get_code("5a36b6fd1493e872")
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 Config. 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

class Config:
    def __init__(self):
        self.dataset = 'cifar10'
        self.batch_size = 32

config = Config()

ARGS = {
    'config': config
}
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 Config — a Config output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Config 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_args Ran
ran on a synthesized input
hatimwen/paddle_hashnet/deploy/inference_python/infer.py
code served (permissive licence) · get_code("a66b5598134a7bcd")
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 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

def str2bool(v):
    return v.lower() in ('true', 't', '1')

ARGS = {
    'add_help': True
}
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 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
get_logger Ran
ran; our contract draft was wrong, not the code
hatimwen/paddle_hashnet/main_multi_gpu.py
code served (permissive licence) · get_code("3d300924bfb82d8f")
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 os
import sys
import tempfile
import logging

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_filename = os.path.join(temp_dir, "test.log")

ARGS = {
    "filename": log_filename,
    "logger_name": "test_logger"
}
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
image_test Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/pre_process.py
code served (permissive licence) · get_code("dff451db0315485c")
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 Compose. 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
from PIL import Image

torch.manual_seed(0)

ARGS = {
    "resize_size": 256,
    "crop_size": 224,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
image_test_10crop Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/pre_process.py
code served (permissive licence) · get_code("9a338479bd269e9b")
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
from PIL import Image

# Create a small test image
test_image = Image.new('RGB', (300, 300), color='red')

ARGS = {
    'resize_size': 256,
    'crop_size': 224,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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
image_train Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/pre_process.py
code served (permissive licence) · get_code("3331c5176304df6a")
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 Compose. 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
from PIL import Image
from torchvision import transforms

torch.manual_seed(0)

# Create a small dummy image for testing
dummy_image = Image.new('RGB', (300, 300), color='red')

ARGS = {
    'resize_size': 256,
    'crop_size': 224
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
inv_lr_scheduler Ran
ran; our contract draft was wrong, not the code
thuml/HashNet/pytorch/src/lr_schedule.py
code served (permissive licence) · get_code("3ce1df52d4a961b8")
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 SGD. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer with multiple param groups
optimizer = SGD([
    {'params': model.weight, 'lr': 0.1},
    {'params': model.bias, 'lr': 0.05}
], lr=0.001)

# Define arguments
ARGS = {
    'param_lr': [0.1, 0.05],
    'optimizer': optimizer,
    'iter_num': 100,
    'gamma': 0.1,
    'power': 0.75,
    'init_lr': 0.001
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
multistep_lr_scheduler Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/lr_schedule.py
code served (permissive licence) · get_code("b0c5a2db3d6ec084")
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 SGD. 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
import torch.optim as optim

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer with multiple param groups
optimizer = optim.SGD([
    {'params': model.weight, 'lr': 0.1},
    {'params': model.bias, 'lr': 0.1}
], lr=0.1)

# param_lr: scaling factors for each param group
param_lr = [1.0, 0.5]

# init_lr: initial learning rate
init_lr = 0.1

# epoch: current epoch number
epoch = 50

ARGS = {
    'param_lr': param_lr,
    'optimizer': optimizer,
    'init_lr': init_lr,
    'epoch': epoch
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
pairwise_loss Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/loss.py
code served (permissive licence) · get_code("1cef1cb746b4c73f")
How it ran

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

import torch
from torch.autograd import Variable

torch.manual_seed(0)

# Create small tensors for the function
batch_size = 2
output_dim = 4
label_dim = 3

# outputs1 and outputs2: feature vectors (batch_size x output_dim)
outputs1 = torch.randn(batch_size, output_dim)
outputs2 = torch.randn(batch_size, output_dim)

# label1 and label2: binary labels (batch_size x label_dim)
# These are used in mm(label1, label2.t()) which requires (batch x label_dim) x (label_dim x batch)
label1 = torch.randint(0, 2, (batch_size, label_dim)).float()
label2 = torch.randint(0, 2, (batch_size, label_dim)).float()

# Parameters
sigmoid_param = 1.0
l_threshold = 15.0
class_num = 1.0

ARGS = {
    'outputs1': outputs1,
    'outputs2': outputs2,
    'label1': Variable(label1),
    'label2': Variable(label2),
    'sigmoid_param': sigmoid_param,
    'l_threshold': l_threshold,
    'class_num': class_num
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
pairwise_loss_updated Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/loss.py
code served (permissive licence) · get_code("77901aeefce81a76")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create small tensors for the function
batch_size = 2
embedding_dim = 4

# outputs1 and outputs2 are embeddings that get matrix multiplied
outputs1 = torch.randn(batch_size, embedding_dim)
outputs2 = torch.randn(batch_size, embedding_dim)

# label1 and label2 are label tensors used to compute similarity
# They need to support .data and be convertible to float
# Using one-hot style labels for clarity
label1 = Variable(torch.LongTensor([[1, 0], [0, 1]]))
label2 = Variable(torch.LongTensor([[1, 0], [0, 1]]))

ARGS = {
    "outputs1": outputs1,
    "outputs2": outputs2,
    "label1": label1,
    "label2": label2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
pil_loader Ran
ran, honoured the contract we drafted
thuml/HashNet/pytorch/src/data_list.py
pointer only (licence: MIT); the stored copy get_code serves, from YuemingJin/MTRCNet-CL, is pointer only (licence: NONE) · get_code("1df9a5ffd9b38c34")
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 YuemingJin/MTRCNet-CL, 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.

step_lr_scheduler Ran
ran on a synthesized input
thuml/HashNet/pytorch/src/lr_schedule.py
code served (permissive licence) · get_code("0dfc49084aa7fa24")
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 SGD. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer with multiple param groups
optimizer = SGD([
    {'params': model.weight, 'lr': 0.001},
    {'params': model.bias, 'lr': 0.001}
], lr=0.001)

# Define the arguments
ARGS = {
    'param_lr': [1.0, 0.5],
    'optimizer': optimizer,
    'iter_num': 10,
    'gamma': 0.1,
    'step': 5,
    'init_lr': 0.001
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
accimage_loader Not yet run
unverified (harvested, no recorded run)
thuml/HashNet/pytorch/src/data_list.py
code served (permissive licence) · get_code("9dcef767571b38d7")
How it ran

no invocation recorded.

make_dataset Not yet run
unverified (harvested, no recorded run)
thuml/HashNet/pytorch/src/data_list.py
pointer only (licence: MIT); the stored copy get_code serves, from Albert0147/AaD_SFDA, is pointer only (licence: NONE) · get_code("2301055cb33836bc")
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 Albert0147/AaD_SFDA, 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. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 9 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 9 later) and 7 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
accimage_loader 39 other papers
39 later
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1907.02665 (2019-07)
Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
and 36 more not named here
pil_loader 28 other papers
28 later
1805.07932 (2018-05)
Bilinear Attention Networks
1807.06587 (2018-07)
Deep Exemplar-based Colorization
1902.09368 (2019-02)
Dual Attention Networks for Visual Reference Resolution in Visual Dialog
and 25 more not named here
make_dataset 15 other papers
15 later · 5 only as an assembly brick
1908.00347 (2019-08)
Central Similarity Quantization for Efficient Image and Video Retrieval
2003.02541 (2020-03)
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
2104.01539 (2021-04)
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
and 12 more not named here
get_logger 2 other papers
2 later
2111.09883 (2021-11)
Swin Transformer V2: Scaling Up Capacity and Resolution
2408.03675 (2024-08)
NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
CalcHammingDist 1 other paper
1 later
2207.00278 (2022-07)
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
image_test 1 other paper
1 later
1908.00347 (2019-08)
Central Similarity Quantization for Efficient Image and Video Retrieval
image_test_10crop 1 other paper
1 later
1908.00347 (2019-08)
Central Similarity Quantization for Efficient Image and Video Retrieval
image_train 1 other paper
1 later
1908.00347 (2019-08)
Central Similarity Quantization for Efficient Image and Video Retrieval
inv_lr_scheduler 1 other paper
1 later
2007.01434 (2020-07)
In Search of Lost Domain Generalization

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep learning to hash, which improves retrieval quality by end-to-end representation learning and hash encoding, has received increasing attention recently. Subject to the ill-posed gradient difficulty in the optimization with sign activations, existing deep learning to hash methods need to first learn continuous representations and then generate binary hash codes in a separated binarization step, which suffer from substantial loss of retrieval quality. This work presents HashNet, a novel deep architecture for deep learning to hash by continuation method with convergence guarantees, which learns exactly binary hash codes from imbalanced similarity data. The key idea is to attack the ill-posed gradient problem in optimizing deep networks with non-smooth binary activations by continuation method, in which we begin from learning an easier network with smoothed activation function and let it evolve during the training, until it eventually goes back to being the original, difficult to optimize, deep network with the sign activation function. Comprehensive empirical evidence shows that HashNet can generate exactly binary hash codes and yield state-of-the-art multimedia retrieval performance on standard benchmarks.

For agents

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

get_harvested_code_for_paper("1702.00758")
get_code_for_paper("1702.00758")
have("1702.00758")

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

curl https://syntology.ai/api/ran/1702.00758.json

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

[![Syntology run record](https://syntology.ai/api/ran/1702.00758.svg)](https://syntology.ai/paper/1702.00758)

Connect an agent — have() is free.