Ruibin Zhang
Ruibin Zhang
After trainning for 17W steps, I can get good results without using dpm-solver in 1000 steps, as shown below:  However, when using dpm-solver in 20, 50, or 1000 steps,...
After setting use_fp16 = True, some bugs occur:  It seems that not all of the models and weights are converted to fp16? Looking forward to your reply, thank you
Thank you for your solid work! I wonder that during your training process of the Camera-to-LiDAR task, is the pretrained CLIP (https://github.com/openai/CLIP) frozen or not? Thank you!