This commit is contained in:
Matteo Bortoletto 2024-02-01 15:44:15 +01:00
parent c6770ac214
commit 11026561b4

View file

@ -24,14 +24,14 @@ If you find our code useful or use it in your own projects, please cite our pape
This code is based on the [original implementation][5] of the BIB benchmark.
## Using `virtualenv`
```
```bash
python -m virtualenv /path/to/env
source /path/to/env/bin/activate
pip install -r requirements.txt
```
## Using `conda`
```
```bash
conda create --name <env_name> python=3.8.10 pip=20.0.2 cudatoolkit=10.2.89
conda activate <env_name>
pip install -r requirements_conda.txt
@ -46,23 +46,23 @@ Run `source bibdgl/bin/activate`.
## Index data
This will create the json files with all the indexed frames for each episode in each video.
```
```bash
python utils/index_data.py
```
You need to manually set `mode` in the dataset class (in main).
## Generate graphs
This will generate the graphs from the videos:
```
```bash
python /utils/build_graphs.py --mode MODE --cpus NUM_CPUS
```
`MODE` can be `train`, `val` or `test`. NOTE: check `utils/build_graphs.py` to make sure you're loading the correct dataset to generate the graphs you want.
## Training
Use `run_train.sh`.
Use `CUDA_VISIBLE_DEVICES=0 run_train.sh`.
## Testing
Use `run_test.sh`.
Use `CUDA_VISIBLE_DEVICES=0 run_test.sh`.
# Hardware setup
All models are trained on an NVIDIA Tesla V100-SXM2-32GB GPU.