Hello, Thanks for open sourcing! I try to run evaluation on GQA but failed.</p

Missing key(s) in state_dict: "contrastive_align_projection_image.weight", "contrastive_align_projection_image.bias", "contrastive_align_projection_text.weight", "contrastive_align_projection_text.bias". about mdetr HOT 2 CLOSED

ashkamath commented on June 27, 2024

Missing key(s) in state_dict: "contrastive_align_projection_image.weight", "contrastive_align_projection_image.bias", "contrastive_align_projection_text.weight", "contrastive_align_projection_text.bias".

from mdetr.

Comments (2)

ashkamath commented on June 27, 2024 1

Hi! for the final finetuning on GQA balanced we do not use the contrastive align loss. That's why those keys aren't in the state dict. So just pass --no_contrastive_align_loss along with the other command line args and it should work. I'll update it in the README too. Thanks!

from mdetr.

MorningStarOvO commented on June 27, 2024

Thank you for your comment! The problem is solved.

from mdetr.

Related Issues (20)

Can you provide the final_vg json files?
Issues with training on a single node
requirements for running the demo notebook HOT 1
Pre-trained model gives nan prediction in Colab HOT 7
Seems cannot verify the existence of objects HOT 2
How to define "Negative Tokens" ? HOT 1
Bbox assertion error when using ENB models (eval & pretrain as well): assert (boxes1[:, 2:] >= boxes1[:, :2]).all() HOT 8
how to define positive tokens? HOT 1
ValueError: char_to_token() is not available when using Python based tokenizers HOT 1
How to generate "tokens_negative" and "tokens_positive" when we convert our own dataset into mdetr annotations? HOT 1
finetune have bug！！ValueError: char_to_token() is not available when using Python based tokenizers HOT 3
Cannot find finetune_phrasecut_miniv.json HOT 1
[Colab Error] InvalidVersion: Invalid version: '0.10.1,<0.11' HOT 2
With the increase of MDETR training time, GPU memory occupation keeps increasing. After several epoch training, memory explodes，i.e. OOM, out of memory. HOT 1
issue #44 "I guess its uncompleted project so I gave up this essay" HOT 1
I would like to know how to use the model in clevr-ref+.
Weird results while evaluating & reproducing ENB3 model on PhraseCut
How to decode GQA evaluation results HOT 1
run
CLEVR-REF+ training

Missing key(s) in state_dict: "contrastive_align_projection_image.weight", "contrastive_align_projection_image.bias", "contrastive_align_projection_text.weight", "contrastive_align_projection_text.bias". about mdetr HOT 2 CLOSED

Comments (2)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent