autodistill / autodistill-detic

DETIC module for use with Autodistill.
https://docs.autodistill.com
MIT License
13 stars 2 forks source link

Unable to see the result: #5

Open shersoni610 opened 1 year ago

shersoni610 commented 1 year ago

Hello,

When I try the DETIC model. I do not see any result : It seems labelled images are zero.

person Loading pretrained CLIP /media/csverma/M2Disk/Projects/CompVis/ObjectDetection/AutoDistill/autodistillenv/lib/python3.11/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3526.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] [10/07 11:40:22 fvcore.common.checkpoint]: [Checkpointer] Loading from models/Detic_LCOCOI21k_CLIP_SwinB_896b32_4x_ft4x_max-size.pth ... Labeling images: 0it [00:00, ?it/s] Labeled dataset created - ready for distillation.

capjamesg commented 1 year ago

Thank you for leaving this Issue. What file extension are the images in the folder that contains the images you want to label?

kamil-bednarek commented 1 year ago

Same here, jpeg and png - same result.

kamil-bednarek commented 1 year ago

I see the possible issue: you should provide an absolute path for the directories.

shersoni610 commented 1 year ago

I gave the complete path. Stil there were issues.

capjamesg commented 1 year ago

@shersoni610 Can you provide a complete code snippet and, if possible, an example image so that we can take a look?