Instructions to use facebook/vit_pe_core_large_patch14_336_timm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PerceptionEncoder
How to use facebook/vit_pe_core_large_patch14_336_timm with PerceptionEncoder:
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("facebook/vit_pe_core_large_patch14_336_timm", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Failed to run. Please update the code as soon as possible
#1
by asdoasfd - opened
Traceback (most recent call last):
File "/home/wujj/dq/output/vlm-output/test.py", line 3, in
model = pe.VisionTransformer.from_config("facebook/vit_pe_core_large_patch14_336_timm", pretrained=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/wujj/perception_models/core/vision_encoder/pe.py", line 443, in from_config
raise RuntimeError(f"{name} not found in configs.")
RuntimeError: facebook/vit_pe_core_large_patch14_336_timm not found in configs.