After training, .h5 is generated. When try to convert the .h5 to PD file, the following error occur.
File "C:\ProgramData\Anaconda3b\envs\gpu59\lib\site-packages\tensorflow\python\keras\saving\hdf5_format.py", line 176, in load_model_from_hdf5
raise ValueError('No model found in config file.')
ValueError: No model found in config file.
The code to convert from .h5 to .pd are:
import tensorflow as tf
After training, .h5 is generated. When try to convert the .h5 to PD file, the following error occur. File "C:\ProgramData\Anaconda3b\envs\gpu59\lib\site-packages\tensorflow\python\keras\saving\hdf5_format.py", line 176, in load_model_from_hdf5 raise ValueError('No model found in config file.') ValueError: No model found in config file.
The code to convert from .h5 to .pd are: import tensorflow as tf
pre_model = tf.keras.models.load_model('best_epoch_weights.H5') tf.saved_model.save(pre_model,"yoloV4_tiny_tf2")
Thanks in advance for any helps.