hdjsjyl

Results 39 comments of hdjsjyl

text_encoder was not finetuned with script examples/images/dreambooth/train_dreambooth_colossalai.py,[BUG]:

hi @JThh , Thanks for your reply. Have you solved this issue?

[FEATURE]: Any plan to support train_dreambooth_colossalai with train_text_encoder?

hi @feifeibear , thanks for your great job! Would you explain a little bit about which part I should change for supporting text_encoder parameters? For my thinking, I put all...

How to fine tune the in-painting version of model?

+1 mark

How to finetune inpainting on custom dataset？

+1 mark

How to get kinematic_chain and raw_offsets?

Hi @EricGuo5513 , Really appreciate your reply. Do you have some suggestions for learning 3D motion to understand the basic definitions in 3D motion data, 3D data rendering, etc? Thank...

Get 100% Missing Rate

@xuw080 Did you get the effective results of this code? Any advice will be appreciated. Thanks

why should fix parameters in training maskrcnn?

@gaosanyuan , I met similar problem to you. I want to ask you where this parameter 'FIXED_PARAMS_SHARED' is used? What's the meaning of this part? Any advice will be appreciated....

why should fix parameters in training maskrcnn?

@gaosanyuan , I get it. Thanks

Is it possible to train for keypoint detection?

@TalkIsCheapGiveMeMoney , Hi, I am working on fitting segmentation to keypoint detection. Do you have some advice. Any advice will be appreciated!

mask-rcnn how to allocate memory, If my own dataset has some big size images like 7127*7127, it has cudo memory error.

@huangzehao , I want to use my own dataset to train the mask rcnn. Actually, the size of images in the dataset varies from 500*1000 to 7000 * 7000. Do...