Li-Yun (James) Wang

Hi, I have a question for training the quantized SSD detector. It seems there is no script to run training. How can I train the quantized detector using this framework?...

RuntimeError: CUDA error: out of memory

2

Hi, I always got the run time error after I ran python eval.py mbv2 --trained_model=checkpoints/student_mbv2_500_3934.pth. Does anyone know how to solve this error? Thanks.

Ground Truth for BVP

1

Hi, Thanks for sharing this dataset publicly. I have a question for this dataset. Does this dataset consist of ground truth BVP? Best, Li-Yun

Hi, It was a good paper, and thanks for releasing the code. I have a question in terms of loss computation for discriminators. In the implementation, you have two discriminator...

Hi, I do have another question for you. I am trying to re-genreate a train.json and a val.json for the cityperson dataset. However, the new val.json file that I created...

Hello, I am able to run testing and evaluate a test file. My question will be how do you train your detector? I assume you can use the train,.py in...

I was trying to run the command "python tools/test.py city_cfgs/mgan_50_65.py models/50_65.pth --out result/50_65.pkl", but I got multiple import-module errors. It seems that the newest version of the mmdetection package has...

Hi, I am trying to train a pre-training model on the CIFAR-10 and CIFAR-100 dataset, but I could not achieve high top-1 classification accuracy while evaluating the pre-trained model using...

Question for the Dataloader

2

Hi, Sorry to have another question for your implementation. In your Dataloader implementation, I notice that you alway return the whole images and feed them to the model for model...

Hi, It is a great work, and thanks for releasing a PyTorch version of your work. I have a quick question for the illumination-aware fusion network training for my own...