Shih Fang Chen

Hi, thanks for this work. I am curious that how to automatically refresh gpuview webpage.

Hi, thanks for your RTS work. I found that the loss for initial filter iteration occasionally overfitting when training. (~110 epochs) Is this usual?  Due to the big GPU...

CPU utils occupies a lot when inference

11

Hi, when inferencing, I notice that the program occupies a lot of CPU load. Before running the program:  After running the program: set the thread as 1  set...

Hi, when I train with dimp dimp50 (multiGPU) with Pytorch 1.12 (w Cuda 11.3) the ATen package gives me some errors, cuz ATen come from vacancy/PreciseRoIPooling so when I move...

Hi, Has this model been implemented without any training process? And is the only required training process the training of HQ-SAM independently? Alternatively, please provide the GPT/memory usage details for...

Hi, thanks for the work. Do you provide the inference time (sparse and dense point sampling) ablation? Such as DOT, 

VGGT-500M and VGGT-200M models

3

Hi, this is great work! Is there an estimated date when we can access the VGGT-500M and VGGT-200M models? I have an additional question: Is the current model trained with...