SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1506.01186 · 2015

Cyclical Learning Rates for Training Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 4 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/1506.01186.json · badge: /api/ran/1506.01186.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
maikherbig/AIDeveloper community (classifier label)
classifier basis not recorded on the link
11 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
mhmoodlan/cyclic-learning-rate community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
davidtvs/pytorch-lr-finder reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Example_sequential_api Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/model_zoo.py
code served (permissive licence) · get_code("cb1b3c9d80104afe")
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 Sequential. 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
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import add, Add, Concatenate, Input, Dense, Dropout, Flatten, Activation, Conv2D, MaxPooling2D, BatchNormalization, GlobalAveragePooling2D, GlobalMaxPooling2D, concatenate

ARGS = {
    'in_dim': 32,
    'channels': 3,
    'out_dim': 10,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from MediaBrain-SJTU/BCL
pointer only · get_code("d9def42110729a85")
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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from lixiaotong97/DSU
pointer only; the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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.

cyclic_learning_rate Ran
ran on a synthesized input
mhmoodlan/cyclic-learning-rate/clr.py
code served (permissive licence) · get_code("a20814d7bfa74719")
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 function. 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 valid arguments for cyclic_learning_rate function
ARGS = {
    'global_step': tf.Variable(5, dtype=tf.int32),
    'learning_rate': 0.01,
    'max_lr': 0.1,
    'step_size': 20.0,
    'gamma': 0.99994,
    'mode': 'triangular',
    'name': 'cyclic_lr_test'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_default_dict Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_start.py
code served (permissive licence) · get_code("0adbffc117bfd132")
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 os
import json
import tempfile

# Create a temporary directory and a settings JSON file
temp_dir = tempfile.mkdtemp()
settings_file = os.path.join(temp_dir, 'settings.json')

# Write a minimal JSON file with some initial settings
initial_settings = {
    'Icon theme': 'Icon theme 2',
    'Path of last model': '/home/user/models'
}

with open(settings_file, 'w') as f:
    json.dump(initial_settings, f)

ARGS = {
    'dir_settings': settings_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 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_metrics_strings Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_dl.py
code served (permissive licence) · get_code("f946f37e1b43a15d")
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 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 numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - model_metrics: iterable of strings that are checked for 'precision', 'recall', 'auc'
# - nr_classes: integer used in range() to create indices

ARGS = {
    'model_metrics': ['precision', 'recall', 'auc'],
    'nr_classes': 3
}
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, ndim 1, 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
get_metrics_tensors Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_dl.py
code served (permissive licence) · get_code("d00620593ea5d2df")
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 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 tensorflow as tf

ARGS = {
    'metrics': [
        'auc',
        'precision',
        'recall'
    ],
    'nr_classes': 3
}
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 list, ndim 1, 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
hashfile Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_bin.py
code served (permissive licence) · get_code("45a9c41a6b24a718")
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 hashlib
import pathlib
import tempfile
import os

# Create a temporary file with some content for testing
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_file.txt")
with open(temp_file, 'w') as f:
    f.write("a" * 100000)  # Write enough content to test blocksize

ARGS = {
    "fname": temp_file,
    "blocksize": 65536,
    "count": 0,
    "constructor": hashlib.md5,
    "hasher_class": None,
}
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 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
image_adjust_channels Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_img.py
code served (permissive licence) · get_code("cf5cbe4cbc370df8")
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 (2, 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

# Test case 1: RGB images to grayscale
rgb_images = np.random.randint(0, 256, size=(2, 4, 5, 3), dtype=np.uint8)

ARGS = {
    "images": rgb_images,
    "target_channels": 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 3, dtype family int, shape (2, 4, 5) — shape (2, 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
model_change_trainability Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_dl.py
code served (permissive licence) · get_code("cd3acc6cca5ab016")
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 tensorflow as tf
import numpy as np

# Create a small Keras model
model_keras = tf.keras.Sequential([
    tf.keras.layers.Dense(8, activation='relu', input_shape=(4,)),
    tf.keras.layers.Dense(3, activation='softmax')
])

# Define loss function
loss_ = 'categorical_crossentropy'

# Define optimizer configuration dict for Adam optimizer
optimizer_ = {
    'comboBox_optimizer': 'adam',
    'doubleSpinBox_lr_adam': 0.001,
    'doubleSpinBox_adam_beta1': 0.9,
    'doubleSpinBox_adam_beta2': 0.999,
    'checkBox_adam_amsgrad': False,
}

# Define learning rate
learning_rate_ = 0.001

# Define model metrics
model_metrics = ['auc', 'precision', 'recall']

# Output dimension (number of classes)
out_dim = 3

# Define trainability states for each layer with parameters
# The model has 2 layers with parameters (Dense layers)
trainable_new = [True, False]

ARGS = {
    'model_keras': model_keras,
    'trainable_new': trainable_new,
    'model_metrics': model_metrics,
    'out_dim': out_dim,
    'loss_': loss_,
    'optimizer_': optimizer_,
    'learning_rate_': learning_rate_
}
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 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
obj2bytes Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_bin.py
code served (permissive licence) · get_code("bf5d386d1b0b6ab0")
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 bytes. 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
import pathlib
import h5py
import tempfile
import os

# Create a temporary HDF5 file for testing
temp_dir = tempfile.mkdtemp()
h5_path = os.path.join(temp_dir, 'test.h5')
with h5py.File(h5_path, 'w') as f:
    f.create_dataset('data', data=np.array([1.0, 2.0, 3.0]))

# Create a stand-in class with an identifier attribute
class ObjectWithIdentifier:
    def __init__(self):
        self.identifier = "test_identifier"

# Test with each type the function handles
ARGS = {
    'obj': "test_string"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
pad_arguments_np2cv Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_img.py
code served (permissive licence) · get_code("7ee2ab117ac91fd6")
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
import numpy as np

# The function takes a single parameter: padding_mode (a string)
# Looking at the function body, it checks various string values and returns a corresponding OpenCV border type string

# Test cases for valid padding modes
ARGS = {
    "padding_mode": "constant"
}
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 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
resnet20 Ran
ran; our contract draft was wrong, not the code
davidtvs/pytorch-lr-finder/examples/cifar10_resnet.py
code served (permissive licence) · get_code("e5d7185b6cba3126")
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 Cifar10ResNet. 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 = {
    "num_classes": 10,
    "ch_width": 2,
}
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 Cifar10ResNet — a Cifar10ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Cifar10ResNet 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
splitall Ran
ran; our contract draft was wrong, not the code
maikherbig/AIDeveloper/AIDeveloper/aid_bin.py
code served (permissive licence) · get_code("8b4838063b92e952")
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 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os

def splitall(path):
    """
    Credit goes to Trent Mick
    SOURCE:
    https://www.oreilly.com/library/view/python-cookbook/0596001673/ch04s16.html
    """
    allparts = []
    while 1:
        parts = os.path.split(path)
        if parts[0] == path:
            allparts.insert(0, parts[0])
            break
        elif parts[1] == path:
            allparts.insert(0, parts[1])
            break
        else:
            path = parts[0]
            allparts.insert(0, parts[1])
    return allparts


ARGS = {
    "path": "/usr/local/bin/python"
}
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 1, 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
zoom_arguments_scipy2cv Ran
ran on a synthesized input
maikherbig/AIDeveloper/AIDeveloper/aid_img.py
code served (permissive licence) · get_code("6cf1a30f40bacfe8")
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 numpy as np

# Construct valid arguments for zoom_arguments_scipy2cv
ARGS = {
    "zoom_factor": 0.9,
    "zoom_interpol_method": 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 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
Example_functional_api Not yet run
unverified (harvested, no recorded run)
maikherbig/AIDeveloper/AIDeveloper/model_zoo.py
code served (permissive licence) · get_code("60d8872644d31774")
How it ran

no invocation recorded.

partial_trainability Not yet run
unverified (harvested, no recorded run)
maikherbig/AIDeveloper/AIDeveloper/partial_trainability.py
code served (permissive licence) · get_code("9f17041c328ef059")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 14 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
4 dated earlier, 682 later · 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
conv1x1 431 other papers
1 dated earlier, 429 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 428 more not named here
splitall 1 other paper
1 later
2412.02402 (2024-12)
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

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

Repositories linked to this paper

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

It is known that the learning rate is the most important hyper-parameter to tune for training deep neural networks. This paper describes a new method for setting the learning rate, named cyclical learning rates, which practically eliminates the need to experimentally find the best values and schedule for the global learning rates. Instead of monotonically decreasing the learning rate, this method lets the learning rate cyclically vary between reasonable boundary values. Training with cyclical learning rates instead of fixed values achieves improved classification accuracy without a need to tune and often in fewer iterations. This paper also describes a simple way to estimate "reasonable bounds" -- linearly increasing the learning rate of the network for a few epochs. In addition, cyclical learning rates are demonstrated on the CIFAR-10 and CIFAR-100 datasets with ResNets, Stochastic Depth networks, and DenseNets, and the ImageNet dataset with the AlexNet and GoogLeNet architectures. These are practical tools for everyone who trains neural networks.

For agents

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

get_harvested_code_for_paper("1506.01186")
get_code_for_paper("1506.01186")
have("1506.01186")

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

curl https://syntology.ai/api/ran/1506.01186.json

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

[![Syntology run record](https://syntology.ai/api/ran/1506.01186.svg)](https://syntology.ai/paper/1506.01186)

Connect an agent — have() is free.