search

foryichuanqi / RESS-Paper-2022.09-Remaining-useful-life-prediction-by-TaFCN

The source code of paper: Trend attention fully convolutional network for remaining useful life estimation in the turbofan engine PHM of CMAPSS dataset. Signal selection, Attention mechanism, and Interpretability of deep learning are explored.
44 stars 1 forks source link

python代码错误 #3

Open leijdjcn opened 1 month ago

leijdjcn commented 1 month ago

Traceback (most recent call last): File "D:\Download files\wenxiandaima\FCN\code\grid_FD_multi_channel_one_FCN_RUL_A2_attention_1out_all_train_for_test.py", line 431, in plot_model(model, to_file=last_path+r"\Flatten.png", show_shapes=True)#########to_file='Flatten.png',last_path+r"\model\FCN_RUL_1out_train_valid_test{}.h5 File "C:\Users\Liyanhui.conda\envs\tensor\lib\site-packages\keras\utils\vis_utils.py", line 421, in plot_model dot = model_to_dot( File "C:\Users\Liyanhui.conda\envs\tensor\lib\site-packages\keras\utils\vis_utils.py", line 151, in model_to_dot if not check_pydot(): File "C:\Users\Liyanhui.conda\envs\tensor\lib\site-packages\keras\utils\vis_utils.py", line 53, in check_pydot except (OSError, pydot.InvocationException): AttributeError: module 'pydot' has no attribute 'InvocationException

How to solve the above situation？

foryichuanqi commented 1 month ago

I suggest that you don't use the model I gave you, and use my code to train a new model for interpretability analysis.细微的环境变化都会造成模型无法使用，我建议你不要使用我给的模型，而是用我的代码训练一个新模型，用于可解释性分析。