Ggtcf

I am trying to create LSTM Autoencoders for time series data. My goal is to use the encoded representation of these sequences which are generated by the autoencoder and classify them. The length of all sequences is really large(around 1M) and I have 9 sequences like this. Hence, I am using fit generators along with the LSTMs to incorporate my data. However, my loss function is not converging and accuracy is really bad for the LSTM Autoencoders. Here is a part of my code.

encoder_input = Input(shape=(None, input_dim))
encoder_output = LSTM(latent_space)(encoder_input)
decoder_input = Lambda(repeat_vector, output_shape=(None, latent_space))([encoder_output, encoder_input])
decoder_out = LSTM(latent_space, return_sequences=True)(decoder_input)
decoder_output = TimeDistributed(Dense(input_dim))(decoder_out)

autoencoder = Model(encoder_input, decoder_output)
encoder = Model(encoder_input, encoder_output)

autoencoder.compile(optimizer="Adam", loss="mse", metrics=["accuracy"])

def generator(X_data, window_size, step_size):

 size_data = X_data.shape[0]
 # print('size:',size_data)

 while 1:

 for k in range(0, size_data - window_size, step_size):
 x_batch = X_data[k:k + window_size, :]
 x_batch = x_batch.reshape(1,x_batch.shape[0], x_batch.shape[1])
 # print(x_batch.shape)
 y_batch = x_batch
 # print("i = " + str(i))
 yield x_batch, y_batch
 # print('value: ', x_batch, y_batch)


sliding_window_size = 200
step_size_of_sliding_window = 200
n_epochs = 50


for epoch in range(n_epochs):
 print("At Iteration: " + str(epoch))
 losses = []
 csv_logger = CSVLogger('log.csv', append=True, separator=';')
 loss = autoencoder.fit_generator(generator(X_tr,sliding_window_size, step_size_of_sliding_window),steps_per_epoch=shots_train,epochs=1,verbose=2,callbacks=[csv_logger])
 losses.append(loss.history['loss'])

I am getting the following results in brief:

Epoch 1/1
- 6s - loss: 0.0319 - acc: 0.5425
At Iteration: 6
Epoch 1/1
- 6s - loss: 0.0326 - acc: 0.4555
At Iteration: 7
Epoch 1/1
- 6s - loss: 0.0301 - acc: 0.4865
At Iteration: 8
Epoch 1/1
- 6s - loss: 0.0304 - acc: 0.5020
At Iteration: 9
Epoch 1/1
- 6s - loss: 0.0313 - acc: 0.4780
At Iteration: 10
Epoch 1/1
- 6s - loss: 0.0313 - acc: 0.5090
At Iteration: 11
Epoch 1/1
- 6s - loss: 0.0313 - acc: 0.4675

The accuracy is really bad and the reconstructed sequence is also different. How can I improve the same? I have already tried using different code sizes in the LSTMs.