【论文复现】复现TSN网络时,训练和测试均出现“TypeError: not all arguments converted during string formatting”问题.
Created by: Momofilm
- 版本、环境信息: AIstudio环境(GPU) 1)PaddlePaddle版本:PaddlePaddle 1.8.0 2)Python:python3.7 3)GPU:v100
- 复现信息:复现TSN视频分类网络(https://aistudio.baidu.com/aistudio/projectdetail/675993)
- 问题描述:‘!python train.py --use_gpu True --epoch 1’运行训练网络时会出现,以下错误: Traceback (most recent call last): File "train.py", line 127, in train(args) File "train.py", line 75, in train train_model = TSN1.TSNResNet('TSN', train_config['MODEL']['num_layers'],train_config['MODEL']['num_classes'],train_config['MODEL']['seg_num'], 0.00002) File "/home/aistudio/model/TSN1.py", line 129, in init act='relu') File "/home/aistudio/model/TSN1.py", line 33, in init bias_attr=False) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/nn.py", line 201, in init if self._num_channels % self._groups != 0: TypeError: not all arguments converted during string formatting 希望得到问题回复!困扰我两天了,无法解决。