When running this statement CUDA_VISIBLE_DEVICES=0 python train.py --dataset scannet --log_dir log_scannet --num_point 40000,
the following error occurs： EPOCH 000
Current learning rate: 0.001000
Current BN decay momentum: 0.500000
2022-04-10 17:22:33.082380
/home/z/anaconda3/envs/v/lib/python3.7/site-packages/numpy/core/fromnumeric.py:3441: RuntimeWarning: Mean of empty slice.
out=out, **kwargs)
/home/z/anaconda3/envs/v/lib/python3.7/site-packages/numpy/core/_methods.py:189: RuntimeWarning: invalid value encountered in double_scalars
ret = ret.dtype.type(ret / rcount)
eval mAP: nan
eval AR: nan
Traceback (most recent call last):
File "train.py", line 334, in
train(start_epoch)
File "train.py", line 321, in train
loss = evaluate_one_epoch()
File "train.py", line 302, in evaluate_one_epoch
mean_loss = stat_dict['loss']/float(batch_idx+1)
KeyError: 'loss'
lschoole
commented
1 year ago
When running this statement CUDA_VISIBLE_DEVICES=0 python train.py --dataset scannet --log_dir log_scannet --num_point 40000, the following error occurs： EPOCH 000 Current learning rate: 0.001000 Current BN decay momentum: 0.500000 2022-04-10 17:22:33.082380 /home/z/anaconda3/envs/v/lib/python3.7/site-packages/numpy/core/fromnumeric.py:3441: RuntimeWarning: Mean of empty slice. out=out, **kwargs) /home/z/anaconda3/envs/v/lib/python3.7/site-packages/numpy/core/_methods.py:189: RuntimeWarning: invalid value encountered in double_scalars ret = ret.dtype.type(ret / rcount) eval mAP: nan eval AR: nan Traceback (most recent call last): File "train.py", line 334, in
train(start_epoch)
File "train.py", line 321, in train
loss = evaluate_one_epoch()
File "train.py", line 302, in evaluate_one_epoch
mean_loss = stat_dict['loss']/float(batch_idx+1)
KeyError: 'loss'
Please help the big guys！！！