Sorry to trouble you， I have a problem about training the keras model.Recently，I used the existing models from keras applications like VGG16,VGG19. The applications provide the existing models which are converted from caffe model. I reproduced the result for inference. But when I want to use the VGG16 model with weights retrain imagenet data,the acc was rised from 0,not a higher acc. First,I think the reason is that tfrecords convert the raw image to (-1.1) but caffe used the raw image which substract mean and convert RGB. Soon, I convert the data in tfrecords look like the data in caffe, but the acc is low too... Second I replace the categorical_crossentropy with sparse_categorical_crossentropy and cancell the one-hot coding. But it doen't work.
I'm sorry for my English is elementary level.
Sorry to trouble you， I have a problem about training the keras model.Recently，I used the existing models from keras applications like VGG16,VGG19. The applications provide the existing models which are converted from caffe model. I reproduced the result for inference. But when I want to use the VGG16 model with weights retrain imagenet data,the acc was rised from 0,not a higher acc. First,I think the reason is that tfrecords convert the raw image to (-1.1) but caffe used the raw image which substract mean and convert RGB. Soon, I convert the data in tfrecords look like the data in caffe, but the acc is low too... Second I replace the categorical_crossentropy with sparse_categorical_crossentropy and cancell the one-hot coding. But it doen't work. I'm sorry for my English is elementary level.