Open hmhwe opened 5 years ago
I tried to run keras model on a browser using keras.js , but I got the following error while loading it
Error: [Model] Model configuration does not contain any layer The kera model is from keras.models import Sequential from keras.layers import Dense, LSTM, InputLayer, Bidirectional, TimeDistributed, Embedding, Activation from keras.optimizers import Adam model = Sequential() model.add(InputLayer(input_shape=(MAX_LENGTH, ))) model.add(Embedding(len(word2index), 128)) model.add(Bidirectional(LSTM(256, return_sequences=True))) model.add(TimeDistributed(Dense(len(tag2index)))) model.add(Activation('softmax'))
Error: [Model] Model configuration does not contain any layer The kera model is
from keras.models import Sequential from keras.layers import Dense, LSTM, InputLayer, Bidirectional, TimeDistributed, Embedding, Activation from keras.optimizers import Adam model = Sequential() model.add(InputLayer(input_shape=(MAX_LENGTH, ))) model.add(Embedding(len(word2index), 128)) model.add(Bidirectional(LSTM(256, return_sequences=True))) model.add(TimeDistributed(Dense(len(tag2index)))) model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer=Adam(0.001), metrics=['accuracy', ignore_class_accuracy(0)])
model.summary()
Then I have converted with encoder.py as > python encoder.py model.hdf5 And load it with keras.js as
cconst model= new KerasJS.Model({ filepath: { model: 'model.json', weights: 'model_weights.buf', metadata: 'model_metadata.json' },
gpu: false })
I have tried with keras version 2.2.4 , 2.1.4, 2.2.2, 2.1.5 and 2.1.4 . Any help would be appreciated.
2.0.6 version removed this error for me
I tried to run keras model on a browser using keras.js , but I got the following error while loading it
model.compile(loss='categorical_crossentropy', optimizer=Adam(0.001), metrics=['accuracy', ignore_class_accuracy(0)])
model.summary()
cconst model= new KerasJS.Model({ filepath: { model: 'model.json', weights: 'model_weights.buf', metadata: 'model_metadata.json' },