Zichen Liang
Zichen Liang
When i run beef with below configs(b0 20steps and b0 10steps) on imagenet100, the loss is nan. But it can be run in b0 5steps normally. Is beef need special...
When i run codes on GPU1, it seems that .cuda() will put data on default GPU and then bugs occurred.
When i run codes on GPU1, it seems that .cuda() will put data on default GPU and then bugs occurred. File "/home/ubuntu/lzc/PyCIL/utils/inc_net.py", line 605, in forward fc_weight = torch.cat([self.old_fc.weight,torch.zeros((new_task_size,self.feature_dim-self.out_dim)).cuda()],dim=0) RuntimeError:...
from ai2thor.controller import Controller from ai2thor.platform import CloudRendering controller = Controller(platform=CloudRendering) Traceback (most recent call last): File "debug.py", line 3, in controller = Controller(platform=CloudRendering) File "/opt/conda/lib/python3.8/site-packages/ai2thor/controller.py", line 518, in __init__...
The [Link](https://mega.nz/folder/fBliUDBL#e-whIrJOCSjfXff7_S5iAQ) appears to contain empty folders.
After completing the training, I couldn't find the FWT, NBT, and AUC results. How can I retrieve them?
When I was training on the ImageNetR dataset using two GPUs, an issue occurred during the second phase of training (it appeared suddenly after a period of normal training). Has...