Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -251,6 +251,8 @@ python run_mvar_evaluate.py \
|
|
| 251 |
|
| 252 |
|
| 253 |
6.2. **Run evaluation:**
|
|
|
|
|
|
|
| 254 |
```bash
|
| 255 |
python utils/evaluations/c2i/evaluator.py \
|
| 256 |
--ref_batch VIRTUAL_imagenet256_labeled.npz \
|
|
|
|
| 251 |
|
| 252 |
|
| 253 |
6.2. **Run evaluation:**
|
| 254 |
+
|
| 255 |
+
We use the [OpenAI's FID evaluation toolkit](https://github.com/openai/guided-diffusion/tree/main/evaluations) and reference ground truth npz file of [256x256](https://openaipublic.blob.core.windows.net/diffusion/jul-2021/ref_batches/imagenet/256/VIRTUAL_imagenet256_labeled.npz) to evaluate FID, IS, Precision, and Recall.
|
| 256 |
```bash
|
| 257 |
python utils/evaluations/c2i/evaluator.py \
|
| 258 |
--ref_batch VIRTUAL_imagenet256_labeled.npz \
|