Shock Jiang
Dear Author(s), I am trying to applying this channel pruning method on a Unet(which is RCNN-like network with residual branch. I have tried weeks to read your python code (Also...
I noticed that there are 130 real rgb-d training images in LineMOD ape, while 1K+ for test. So It is very important to generate render/fuse data. I wonder the parameters,...
I tried to compare the output generated by SID (O-sid) and photoshop (O-ps, with all auto from DNG to PNG), and according to what I saw: 1/ when the light...
Hi, I try to reproduce your experiments on Linemod. Since you have different models for different objects, does that imply you split dataset to multiple and train for different objects?...
the current code is quite slow, which takes about 20 seconds to generate a picture. So I speed it up by using GPU. I set the HL_TARGET and other environment...
### Preliminary Checks - [X] This issue is not a duplicate. Before opening a new issue, please search existing issues. - [X] This issue is not a question, bug report,...
prompt ends with dot
``` llava_name_or_path='hub/llava-phi-3-mini-xtuner' model = dict( type=LLaVAModel, freeze_llm=True, freeze_visual_encoder=True, pretrained_pth=llava_name_or_path, llm=dict( type=AutoModelForCausalLM.from_pretrained, pretrained_model_name_or_path=llm_name_or_path, attn_implementation="eager", trust_remote_code=True), visual_encoder=dict( type=CLIPVisionModel.from_pretrained, pretrained_model_name_or_path=visual_encoder_name_or_path)) ``` when loadding model, the following error occurs: ``` [rank7]: obj = obj_cls(**args)...
I try to load pretrained pth of llava: hub/llava-phi-3-mini-pth/model.pth. And I got this strange error: - used deepspeed zerospeed3 and flash-attn. ``` RuntimeError: Error(s) in loading state_dict for LLaVAModel: size...
hi, after I created the conda env, I run the experiments, I met the follwoing warning. I wonder does this affect my training and final result. thx.