8000 RuntimeError: Invalid pretrained config, cannot load weights. Use `pretrained=False` for random init. · Issue #95 · dandelin/ViLT · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

RuntimeError: Invalid pretrained config, cannot load weights. Use pretrained=False for random init. #95

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
nameyun opened this issue Sep 7, 2024 · 0 comments
Open

RuntimeError: Invalid pretrained config, cannot load weights. Use pretrained=False for random init. #95

nameyun opened this issue Sep 7, 2024 · 0 comments

Comments

@nameyun
Copy link
nameyun commented Sep 7, 2024

Dear Author
When I change 【pretrain=False】 to 【pretrain=True】, as shown in Figure 1, Then use the command 【python run.py with data_root=/root/autodl-tmp/ViLT/csdia_arrow num_gpus=1 task_finetune_vqa_randaug per_gpu_batchsize=64 load_path="/root/autodl-tmp/vilt_200k_mlm_itm.ckpt"】 When pretraining, the following error occurs【RuntimeError: Invalid pretrained config, cannot load weights. Use pretrained=False for random init.】，as shown in Figure 2.

How to solve this problem？

Figure 1：
image

Figure 2：
image
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@nameyun
0