lightly
First Steps
Lightly at a Glance
How Lightly Works
Data and Transformations
Training
Embeddings
Lightly in Three Lines
What’s next?
Benchmarks
CIFAR10
Getting Started
Supported Python versions
Installing Lightly
Dependencies
Next Steps
Command-line tool
Train a model using the CLI
Create embeddings using the CLI
Upload data using the CLI
Upload embeddings using the CLI
Download data using the CLI
Advanced
Augmentations
Models
Losses
Memory Bank
Extracting specific Video Frames
The Lightly Platform
Basic Concepts
Dataset
Upload Samples
Tag
Embedding
Obtaining Good Embeddings
Create a Dataset
Upload Images
Upload Embeddings
Sampling
Dataset Identifier
Authentication API Token
Tutorials
Python Package
Tutorial 1: Structure Your Input
Supported File Types
Images
Videos
Image Folder Datasets
Flat Directory Containing Images
Directory with Subdirectories Containing Images
Video Folder Datasets
Embedding Files
Advanced usage of Embeddings
Next Steps
Tutorial 2: Train MoCo on CIFAR-10
Imports
Configuration
Setup data augmentations and loaders
Create the MoCo Lightning Module
Create the Classifier Lightning Module
Train the MoCo model
Tutorial 3: Train SimCLR on Clothing
Imports
Configuration
Setup data augmentations and loaders
Create the SimCLR model
Train the Embedding
Visualize Nearest Neighbors
Color Invariance
Tutorial 4: Train SimSiam on Satellite Images
Imports
Configuration
Setup data augmentations and loaders
Create the SimSiam model
Train SimSiam
Scatter Plot and Nearest Neighbors
Tutorial 5: Custom Augmentations
Imports
Configuration
Setup custom data augmentations
Setup dataset and dataloader
Create the MoCo model
Setup criterion and optimizer
Train MoCo with custom augmentations
Evaluate the results
Platform
Tutorial 1: Curate Pizza Images
What you will learn
Requirements
Upload the data
Filter the dataset using metadata
Download the curated dataset
Training a model using the curated data
Python API
lightly
.core
lightly.api
.upload
.download
.utils
lightly.cli
.lightly_cli
.train_cli
.embed_cli
.upload_cli
.download_cli
.config.config.yaml
Overwrites
Additional Arguments
Default Settings
lightly.data
.collate
.dataset
lightly.embedding
.embedding
lightly.loss
.ntx_ent_loss
.sym_neg_cos_sim_loss
.memory_bank
lightly.models
.resnet
.simclr
.moco
.simsiam
.zoo
lightly.transforms
.gaussian_blur
.rotation
lightly.utils
.io
.embeddings_2d
On-Premise
Docker
Setup
Analytics
Licensing
Download image
First Steps
Storage Access
Embedding and Sampling a Dataset
Train a Self-Supervised Model
Accessing Lightly Input Parameters
Sampling from Embeddings File
Sampling from Video Files
Removing Exact Duplicates
Reporting
Docker Output
Evaluation of the Sampling Proces
Advanced
Meta Information
Mask Samples
Use Pre-Selected Samples
Custom Weak Labels
Datapool
How It Works
Usage
Configuration
List of Parameters
Choosing the Right Parameters
Increase I/O Performance
Examples
Extract Diverse Video Frames
Using ffmpeg
Using Lightly Docker
ImageNet
lightly
»
Index
Index
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
N
|
P
|
R
|
S
|
T
|
U
B
BaseCollateFunction (class in lightly.data.collate)
BasicBlock (class in lightly.models.resnet)
Bottleneck (class in lightly.models.resnet)
C
check_filename() (in module lightly.api.utils)
check_image() (in module lightly.api.utils)
checkpoints() (in module lightly.models.zoo)
D
download_cli() (in module lightly.cli.download_cli)
dump() (lightly.data.dataset.LightlyDataset method)
E
embed() (lightly.embedding.embedding.SelfSupervisedEmbedding method)
embed_cli() (in module lightly.cli.embed_cli)
embed_images() (in module lightly.core)
F
fit() (lightly.utils.embeddings_2d.PCA method)
fit_pca() (in module lightly.utils.embeddings_2d)
forward() (lightly.data.collate.BaseCollateFunction method)
(lightly.loss.memory_bank.MemoryBankModule method)
(lightly.loss.ntx_ent_loss.NTXentLoss method)
(lightly.loss.sym_neg_cos_sim_loss.SymNegCosineSimilarityLoss method)
(lightly.models.moco.MoCo method)
(lightly.models.resnet.BasicBlock method)
(lightly.models.resnet.Bottleneck method)
(lightly.models.resnet.ResNet method)
(lightly.models.simclr.SimCLR method)
(lightly.models.simsiam.SimSiam method)
from_torch_dataset() (lightly.data.dataset.LightlyDataset class method)
G
GaussianBlur (class in lightly.transforms.gaussian_blur)
get_filenames() (lightly.data.dataset.LightlyDataset method)
get_meta_from_img() (in module lightly.api.utils)
get_request() (in module lightly.api.utils)
get_samples_by_tag() (in module lightly.api.download)
get_thumbnail_from_img() (in module lightly.api.utils)
getenv() (in module lightly.api.utils)
I
image_mean() (in module lightly.api.utils)
image_std() (in module lightly.api.utils)
ImageCollateFunction (class in lightly.data.collate)
L
lightly
module
lightly.api
module
lightly.api.download
module
lightly.api.upload
module
lightly.api.utils
module
lightly.cli
module
lightly.cli.download_cli
module
lightly.cli.embed_cli
module
lightly.cli.lightly_cli
module
lightly.cli.train_cli
module
lightly.cli.upload_cli
module
lightly.core
module
lightly.data
module
lightly.data.collate
module
lightly.data.dataset
module
lightly.embedding
module
lightly.embedding.embedding
module
lightly.loss
module
lightly.models
module
lightly.models.moco
module
lightly.models.resnet
module
lightly.models.simclr
module
lightly.models.simsiam
module
lightly.models.zoo
module
lightly.transforms
module
lightly.transforms.gaussian_blur
module
lightly.transforms.rotation
module
lightly.utils
module
lightly.utils.embeddings_2d
module
lightly.utils.io
module
lightly_cli() (in module lightly.cli.lightly_cli)
LightlyDataset (class in lightly.data.dataset)
load_embeddings() (in module lightly.utils.io)
load_embeddings_as_dict() (in module lightly.utils.io)
M
MemoryBankModule (class in lightly.loss.memory_bank)
MoCo (class in lightly.models.moco)
MoCoCollateFunction (class in lightly.data.collate)
module
lightly
lightly.api
lightly.api.download
lightly.api.upload
lightly.api.utils
lightly.cli
lightly.cli.download_cli
lightly.cli.embed_cli
lightly.cli.lightly_cli
lightly.cli.train_cli
lightly.cli.upload_cli
lightly.core
lightly.data
lightly.data.collate
lightly.data.dataset
lightly.embedding
lightly.embedding.embedding
lightly.loss
lightly.models
lightly.models.moco
lightly.models.resnet
lightly.models.simclr
lightly.models.simsiam
lightly.models.zoo
lightly.transforms
lightly.transforms.gaussian_blur
lightly.transforms.rotation
lightly.utils
lightly.utils.embeddings_2d
lightly.utils.io
N
NTXentLoss (class in lightly.loss.ntx_ent_loss)
P
PCA (class in lightly.utils.embeddings_2d)
PIL_to_bytes() (in module lightly.api.utils)
post_request() (in module lightly.api.utils)
put_request() (in module lightly.api.utils)
R
RandomRotate (class in lightly.transforms.rotation)
resize_image() (in module lightly.api.utils)
ResNet (class in lightly.models.resnet)
ResNetGenerator() (in module lightly.models.resnet)
S
save_embeddings() (in module lightly.utils.io)
SelfSupervisedEmbedding (class in lightly.embedding.embedding)
shape() (in module lightly.api.utils)
sharpness() (in module lightly.api.utils)
signal_to_noise_ratio() (in module lightly.api.utils)
SimCLR (class in lightly.models.simclr)
SimCLRCollateFunction (class in lightly.data.collate)
SimSiam (class in lightly.models.simsiam)
size_in_bytes() (in module lightly.api.utils)
sum_of_squares() (in module lightly.api.utils)
sum_of_values() (in module lightly.api.utils)
SymNegCosineSimilarityLoss (class in lightly.loss.sym_neg_cos_sim_loss)
T
train_cli() (in module lightly.cli.train_cli)
train_embedding_model() (in module lightly.core)
train_model_and_embed_images() (in module lightly.core)
transform() (lightly.utils.embeddings_2d.PCA method)
U
upload_cli() (in module lightly.cli.upload_cli)
upload_dataset() (in module lightly.api.upload)
upload_embeddings_from_csv() (in module lightly.api.upload)
upload_file_with_signed_url() (in module lightly.api.upload)
upload_images_from_folder() (in module lightly.api.upload)