莫言于方
2020-09-06 20:25
老师,在GPU里训练的模型,在CPU里运行的程序调用,出错,怎么解决呢?
Traceback (most recent call last):
File "demo.py", line 41, in <module>
model = pr.LPR(args.cascade_model_path, args.mapping_vertical_model_path, args.ocr_plate_model_path)
File "/home/yuy/Demo/HyperLPR/HyperLPRLite.py", line 19, in __init__
self.modelSeqRec = self.model_seq_rec(model_seq_rec)
File "/home/yuy/Demo/HyperLPR/HyperLPRLite.py", line 102, in model_seq_rec
base_model.load_weights(model_path)
File "/home/yuy/.virtualenvs/CarEnv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 2211, in load_weights
hdf5_format.load_weights_from_hdf5_group(f, self.layers)
File "/home/yuy/.virtualenvs/CarEnv/lib/python3.6/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 698, in load_weights_from_hdf5_group
layer, weight_values, original_keras_version, original_backend)
File "/home/yuy/.virtualenvs/CarEnv/lib/python3.6/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 408, in preprocess_weights_for_loading
return _convert_rnn_weights(layer, weights)
File "/home/yuy/.virtualenvs/CarEnv/lib/python3.6/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 569, in _convert_rnn_weights
raise ValueError('%s is not compatible with %s' % types)
ValueError: GRU(reset_after=False) is not compatible with GRU(reset_after=True)
那就用cpu 重新训练呗
TensorFlow与Flask结合打造手写体数字识别
20432 学习 · 102 问题
相似问题