baibizhe

Question on extreme result of my own data

3

Hello. I trained this algorithm on my own dataset, and the result seems wired  What would be the potential reason that causes this wired result? Thanks .

这部分我可以来

Is there any paramters that we could edit in order to get a better model?

1

Thanks for this interesting work. We found this work runs pretty fast . However, the metrics are not good enough for us. So, are there any parameters we could edit...

**Is your feature request related to a problem? Please describe.** No **Describe the solution you'd like** Add support for 3D/2D mobile net , mobile nets might be a good choice...

**Is your feature request related to a problem? Please describe.** No **Describe the solution you'd like** Add support for 3D/2D mobile net , mobile nets might be a good choice...

I am trying to feed 512 x 512 image to model with out any resizing . But the performance is pretty low. How should I modify the model in order...

[import jittor will try to download NCCL even NCCL is loaded]

1

## Describe the bug jittor维护者你好 我们试图在超算集群上安装jittor，解决了一些链接问题后，最后还是有一个关于NCCL的问题， 就是我们的gpu节点或者计算节点是没有网络权限的，但是jittor坚持要下载NCCL 即使NCCL已经被load进来了，有没有什么办法在import jittor 的时候 不下载NCCL呢 Hello, jittor maintainer. We tried to install jittor on the supercomputing cluster. After solving some link problems, there was...

Where is your difference between mmseg

1

Hello .Thanks for your wonderful work. What is your different compared to mmseg?Since both of ssseg and mmseg are based on mmcv and need a config to run .

GPU memory of ZeroDepth

3

Hello. I am try to inference with ```zerodepth_model = torch.hub.load("TRI-ML/vidar", "ZeroDepth", pretrained=True, trust_repo=True)``` However , it is only possible if I resize input image to a extreme small size.For example,...

Load pretrained weight error

13

running script: ```sh export PYTHONPATH=. accelerate launch --config_file=./pipeline/accelerate_configs/accelerate_config_fsdp.yaml \ ./pipeline/train/instruction_following.py \ --pretrained_model_name_or_path=luodian/OTTER-9B-INIT \ --mimicit_path="/home/ubuntu/works/code/working_proj/otter/data/xxxjson" \ --images_path="/home/ubuntu/works/code/working_proj/otter/data/xxx.json" \ --train_config_path="/home/ubuntu/works/code/working_proj/otter/data/xxx.json" \ --batch_size=4 \ --num_epochs=9 \ --report_to_wandb \ --wandb_entity=ntu-slab \ --run_name=otter9B_dense_caption \ --wandb_project=otter9B...