Xiaokang Chen

Question about results on ScanNet. Why result of paper v2 is significantly higher than that of paper v1?

3

Hi, I have a question about the results on ScanNet dataset. I find that [email protected] is reported to be **46.75%** in the first version of your paper, while [email protected] is...

Dear author: Thanks for your sharing. Could you supply more details on how to visualize the voxel data in meshlab? I try to write the voxel data into .ply file...

Hello! I am confused with one of your file: 'camera_rotations_NYU.txt'. Under my understanding, this file contains 1449 matrices whose index is corresponding to the index of image_data in 'nyu_depth_v2_labeled.mat'. I...

Occurring error when I add new tokens to the tokenizer.

6

Hi, I want to add new tokens to the tokenizer through: ``` tokenizer.add_tokens("", special_tokens=True) tokenizer.add_tokens("", special_tokens=True) model.resize_token_embeddings(len(tokenizer)) model.config.vocab_size = len(tokenizer) ``` Then I save the model as LoRA adapters through:...

Some weights of the model checkpoint were not used when initializing MGMLlamaForCausalLM

2

When loading the pretrained ckeckpoint after stage 2, I get the following warning: ``` Some weights of the model checkpoint at /train_logs/MGM/MGM-7B/mgm_v7b_336_hr_768_stage2 were not used when initializing MGMLlamaForCausalLM: ['model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight',...

Network performance is getting worse

2

Hi, Thank you for your work and sharing. I try to use `convert_model` function on my own code, for example: ``` cudnn.benchmark = True net = Network() net.cuda() net =...