SimCLR weights (ResNet50, 256 batch size, 100 epochs)

config.yaml

{
  "batch_size": 256,
  "dataset": "STL10",
  "epochs": 100,
  "fp16": false,
  "fp16_opt_level": "O2",
  "logistic_batch_size": 256,
  "logistic_epochs": 100,
  "model_num": 40,
  "model_path": "logs/0",
  "normalize": true,
  "optimizer": "Adam",
  "projection_dim": 64,
  "resnet": "resnet50",
  "seed": 42,
  "start_epoch": 0,
  "temperature": 0.5,
  "workers": 16
}

SimCLR weights (ResNet18, 256 batch size, 100 epochs)

config.yaml:

# train options
seed: 42 # sacred handles automatic seeding when passed in the config
batch_size: 256
workers: 16
start_epoch: 0
epochs: 100
dataset: "STL10" # STL10

# model options
resnet: "resnet18"
normalize: True
projection_dim: 64 # "[...] to project the representation to a 128-dimensional latent space"

# loss options
optimizer: "Adam" # or LARS (experimental)
temperature: 0.5 # see appendix B.7.: Optimal temperature under different batch sizes

# reload options
model_path: "logs/0" # set to the directory containing `checkpoint_##.tar` 
model_num: 40 # set to checkpoint number

# mixed-precision training
fp16: False 
fp16_opt_level: "O2"


# logistic regression options
logistic_batch_size: 256
logistic_epochs: 100

SimCLR weights (40 epochs)

A pre-trained SimCLR model with the following parameters:
"batch_size": 256,
"epochs": 40,
"n_out": 64,
"normalize": true,
"resnet": "resnet18",
"seed": 634715003,
"start_epoch": 0,
"temperature": 0.5,
"workers": 16

Accuracy with a logistic regression classifier trained on top of SimCLR on STL-10 test set: 0.72