mirrors/SimCLR
1
0
Fork 0
mirror of https://github.com/sthalles/SimCLR.git synced 2025-06-03 15:03:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Thalles Silva 2020-02-25 08:49:51 -03:00 committed by GitHub
parent c138e77bdc
commit d1ee7ba4ae
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -1,2 +1,18 @@
# PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations # PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
Check out the Blog post with full documentation: [Exploring SimCLR: A Simple Framework for Contrastive Learning of Visual Representations](https://sthalles.github.io/simple-self-supervised-learning/)
## Config file
Before runing SimCLR, make sure you choose the correct running configurations on the ```config.yaml``` file.
```
batch_size: 256 # A batch size of N, produces 2 * (N-1) negative samples. Original implementation uses a batch size of 8192
out_dim: 64 # Output dimensionality of the embedding vector z. Original implementation uses 2048
s: 1
temperature: 0.5 # Temperature parameter for the contrastive objective
base_convnet: "resnet18" # The ConvNet base model. Choose one of: "resnet18 or resnet50". Original implementation uses resnet50
use_cosine_similarity: True # Distance metric for contrastive loss. If False, uses dot product
epochs: 40 # Number of epochs to train
num_workers: 4 # Number of workers for the data loader
```