pdx.seg.DeepLabv3p语义分割网络训练完一个epoch总是在评估时报错
Created by: minhoooo1
2020-09-19 18:47:09 [INFO] There are 90 varaibles in output/deeplab/pretrain/UNet_COCO are loaded. 2020-09-19 18:47:21 [INFO] [TRAIN] Epoch 1 finished, loss=0.164, lr=0.009892 . 2020-09-19 18:47:21 [INFO] Start to evaluating(total_samples=100, total_steps=25)... 0%| | 0/25 [00:00<?, ?it/s]share_vars_from is set, scope is ignored. 0%| | 0/25 [00:03<?, ?it/s] 。。。。。。。。。。。 /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/scipy/sparse/coo.py in _check(self) 283 if self.nnz > 0: 284 if self.row.max() >= self.shape[0]: --> 285 raise ValueError('row index exceeds matrix dimensions') 286 if self.col.max() >= self.shape[1]: 287 raise ValueError('column index exceeds matrix dimensions') ValueError: row index exceeds matrix dimensions (最后一行的报错内容)