Intel
/

dpt-large

Depth Estimation Transformers PyTorch Safetensors dpt vision Eval Results Inference Endpoints

Model card Files Files and versions Community

Some weights of DPTForDepthEstimation were not initialized from the model checkpoint at Intel/dpt-large

#9

by jigu - opened Jan 16

jigu

Jan 16

It results from https://github.com/huggingface/transformers/blob/edb170238febf7fc3e3278ed5b9ca0b2c40c70e3/src/transformers/models/dpt/modeling_dpt.py#L791. The weight of the first residual layer (although not used) is not in the checkpoint.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment