-
Couldn't load subscription status.
- Fork 6.5k
Closed
Labels
bugSomething isn't workingSomething isn't workingstaleIssues that haven't received updatesIssues that haven't received updates
Description
Describe the bug
Using https://huggingface.co/docs/diffusers/conceptual/evaluation
to measure the clip_score clip_similarity, FID
clip_similarity have problem
It looks the array dimension issue
Change all idx to following
dataset[idx]["image"] to dataset["image"][idx]
also need to take the compatibility version for pillow my case from 9.0.1 to 10.4.0
Reproduction
Using sample code
Using https://huggingface.co/docs/diffusers/conceptual/evaluation
Logs
No response
System Info
Copy-and-paste the text below in your GitHub issue and FILL OUT the two last points.
- 🤗 Diffusers version: 0.29.2
- Platform: Linux-6.5.0-41-generic-x86_64-with-glibc2.35
- Running on a notebook?: No
- Running on Google Colab?: No
- Python version: 3.10.12
- PyTorch version (GPU?): 2.5.0.dev20240629+cu124 (True)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Huggingface_hub version: 0.23.4
- Transformers version: 4.41.2
- Accelerate version: 0.33.0
- PEFT version: not installed
- Bitsandbytes version: not installed
- Safetensors version: 0.4.3
- xFormers version: not installed
- Accelerator: NVIDIA H100 80GB HBM3, 81559 MiB
NVIDIA H100 80GB HBM3, 81559 MiB
NVIDIA H100 80GB HBM3, 81559 MiB
NVIDIA H100 80GB HBM3, 81559 MiB VRAM - Using GPU in script?:
- Using distributed or parallel set-up in script?:
Who can help?
No response
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't workingstaleIssues that haven't received updatesIssues that haven't received updates