microsoft / microsoft/TRELLIS

Error to loading pre-trained model with torchsparse backend

Open
#111 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.7k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

Error

RuntimeError: Error(s) in loading state_dict for SLatMeshDecoder:
        Missing key(s) in state_dict: "upsample.0.out_layers.0.conv.kernel", "upsample.0.out_layers.3.conv.kernel", "upsample.0.skip_connection.conv.kernel", "upsample.1.out_layers.0.conv.kernel", "upsample.1.out_layers.3.conv.kernel", "upsample.1.skip_connection.conv.kernel". 
        Unexpected key(s) in state_dict: "upsample.0.out_layers.0.conv.weight", "upsample.0.out_layers.3.conv.weight", "upsample.0.skip_connection.conv.weight", "upsample.1.out_layers.0.conv.weight", "upsample.1.out_layers.3.conv.weight", "upsample.1.skip_connection.conv.weight".

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the pretrained-model load with the torchsparse backend and inspect the SLatMeshDecoder state_dict mismatch. Trace where the checkpoint and decoder define the listed kernel and weight keys. Done means the model loads without the reported missing and unexpected-key errors.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.