Jiyong Kwag

Hello, Thank you for your great work! As I am working on map change detection (including TbV code), I encounter the problem on SynchronizationDB class. (line 123) ``` for log_fpath...

Hello, Thank you for nice work and sharing with us! As I am working through training I encountered problem.  Training does not proceed after this point. I check the...

Hello, Thank you for your great work! Is it possible that you can share the log file that you generate from rending, training and testing? because I encounter ``` Traceback...

##================= Image Captioning ========================## decoder_input_ids = text_tokens.input_ids.clone() decoder_input_ids[:, 0] = self.tokenizer.bos_token_id labels = decoder_input_ids.masked_fill( decoder_input_ids == self.tokenizer.pad_token_id, -100 ) query_atts = torch.ones(query_tokens.size()[:-1], dtype=torch.long).to( image.device ) attention_mask = torch.cat([query_atts, text_tokens.attention_mask], dim=1)...

Is it possible to use simple multi head self attention on bevformer encoder?

1

Hello, Thank you for your work. I am wondering is there any experiments that simple self attention is used for temporal self attention layer? instead of deformable self-attention? I know...

hello, Thank you for sharing your great work! When you are matching pixel-text score loss, you are using cross entropy between score map S and ground truth segmentation label Y....

GPU memory comsumption increases every epoch during training

2

Hello, Thank you for sharing your work! As I am training on ImageNet1K, I noticed that memory consumption increases by approximately 254MB with each epoch. If this trend continues, the...

Hello, Thank you for your great works! https://github.com/apple/ml-cvnets/blob/77717569ab4a852614dae01f010b32b820cb33bb/cvnets/layers/linear_attention.py#L163-L191 As I am looking at the implementation for the MobileViTV2 Linear Attention, I saw query and key values are generated from x_prev...