error when training pointconv model for part segmentation task #8
Description
Hi, all,
I can train the pointnet and pointnet++ model for the part segmentation task successfully. Here is my command:
python train_partseg.py --model pointnet. However, when I train the pointconv model using the similar command:
python train_partseg.py --model pointconv. I got the following error inconsistent numbers of samples:
Traceback (most recent call last):
File "train_partseg.py", line 271, in <module>
train(model, args, dir_path)
File "train_partseg.py", line 143, in train
train_acc = metrics.accuracy_score(train_true_cls, train_pred_cls)
File "/root/anaconda3/envs/pytorch1.4/lib/python3.7/site-packages/sklearn/utils/validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "/root/anaconda3/envs/pytorch1.4/lib/python3.7/site-packages/sklearn/metrics/_classification.py", line 202, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "/root/anaconda3/envs/pytorch1.4/lib/python3.7/site-packages/sklearn/metrics/_classification.py", line 83, in _check_targets
check_consistent_length(y_true, y_pred)
File "/root/anaconda3/envs/pytorch1.4/lib/python3.7/site-packages/sklearn/utils/validation.py", line 263, in check_consistent_length
" samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [28680192, 700200]
Could you give some hints to tackle this issue?
Thanks~