diff --git a/README.md b/README.md index e09a56521dca12d9b41db28ffc049dc1df0a075d..5591619fee77ca338ff81834ac283707cdbf6d94 100644 --- a/README.md +++ b/README.md @@ -84,6 +84,41 @@ options: --nolog Don't log to wandb (default: False) ``` +### Reproducing SNN baseline + +From the paper "Event-Based Angular Velocity Regression with Spiking Networks" ([code](https://github.com/uzh-rpg/snn_angular_velocity)) + +Download their model weights: + +```bash +wget "http://rpg.ifi.uzh.ch/data/snn_angular_velocity/models/pretrained.pt" -O cnn5-avgp-fc1.pt +``` + +Then run *this* test script: + +```bash +./test_snn.py SNN_baseline cnn-avgp-fc1.pt path-to-dataset/ +``` + +```none +usage: test_snn.py [-h] [--limit_test LIMIT_TEST] [--nolog] [-a BATCH_ACCUMULATION] [-w WORKERS] name checkpoint_path dataset_path + +positional arguments: + name Name of run + checkpoint_path Path to provided checkpoint (cnn5-avgp-fc1.pt) + dataset_path Dataset directory + +options: + -h, --help show this help message and exit + --limit_test LIMIT_TEST + Use this test set proportion (float) or batches (int) each epoch (still randomised over entire dataset) (default: None) + --nolog Don't log to wandb (default: False) + -a BATCH_ACCUMULATION, --batch_accumulation BATCH_ACCUMULATION + Perform batch accumulation (default: 1) + -w WORKERS, --workers WORKERS + Dataset workers (can use 0) (default: 12)``` +``` + ### Training Example: