dayan2020
commented
3 years ago training is ok, but, when I trying evaluation, I meet a problem like this: [Loading model from /home/lijingqin/codes/NoduleNet/results/cross_val_test/model/200.ckpt] out_dir /home/lijingqin/codes/NoduleNet/results/cross_val_test Total # of eval data 83 [0] Predicting 1.3.6.1.4.1.14519.5.2.1.6279.6001.603166427542096384265514998412 (281, 234, 306) Traceback (most recent call last): File "test.py", line 114, in eval net.forward(input, truth_bboxes, truth_labels, truth_masks, mask) File "/home/lijingqin/codes/NoduleNet/net/nodule_net.py", line 390, in forward fpr_res = get_probability(self.cfg, self.mode, inputs, self.rpn_proposals, self.rcnn_logits, self.rcnn_deltas) File "/home/lijingqin/NoduleNet-master/NoduleNet-master/env/lib/python3.5/site-packages/torch/nn/modules/module.py", line 539, in getattr type(self).name, name)) AttributeError: 'NoduleNet' object has no attribute 'rcnn_logits'
and I found the rpn_proposals = 0 and the rpn probability is abnormal.
I have the same problem, how did you solve it
training is ok, but, when I trying evaluation, I meet a problem like this: [Loading model from /home/lijingqin/codes/NoduleNet/results/cross_val_test/model/200.ckpt] out_dir /home/lijingqin/codes/NoduleNet/results/cross_val_test Total # of eval data 83 [0] Predicting 1.3.6.1.4.1.14519.5.2.1.6279.6001.603166427542096384265514998412 (281, 234, 306) Traceback (most recent call last): File "test.py", line 114, in eval net.forward(input, truth_bboxes, truth_labels, truth_masks, mask) File "/home/lijingqin/codes/NoduleNet/net/nodule_net.py", line 390, in forward fpr_res = get_probability(self.cfg, self.mode, inputs, self.rpn_proposals, self.rcnn_logits, self.rcnn_deltas) File "/home/lijingqin/NoduleNet-master/NoduleNet-master/env/lib/python3.5/site-packages/torch/nn/modules/module.py", line 539, in getattr type(self).name, name)) AttributeError: 'NoduleNet' object has no attribute 'rcnn_logits'
and I found the rpn_proposals = 0 and the rpn probability is abnormal.