I try to use your generator for my case, where:
lookback = 1440 = 5 days (timeframe = 5 minutes)
step =1, i.e. my observations will be sampled at one data point per 5 minutes (is it correct?).
I got an error:
2020-12-24 16:58:21.666986: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at random_op.cc:74 : Resource exhausted: OOM when allocating tensor with shape[605924640,32] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
Besides I would like to know an example of model.predict in this case.
And one more question:
What is the way to appky the model
model = Sequential()
model.add(layers.Embedding(max_features, 128))
model.add(layers.LSTM(32))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['acc'])
history = model.fit(x_train, y_train,
epochs=10,
batch_size=128,
validation_split=0.2)
Hello!
I try to use your generator for my case, where: lookback = 1440 = 5 days (timeframe = 5 minutes) step =1, i.e. my observations will be sampled at one data point per 5 minutes (is it correct?).
I got an error: 2020-12-24 16:58:21.666986: W tensorflow/core/framework/op_kernel.cc:1763] OP_REQUIRES failed at random_op.cc:74 : Resource exhausted: OOM when allocating tensor with shape[605924640,32] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
Besides I would like to know an example of model.predict in this case. And one more question: What is the way to appky the model
to my case?