python - Keras - Input a 3 channel image into LSTM

Question

I have read a sequence of images into a numpy array with shape (7338, 225, 1024, 3) where 7338 is the sample size, 225 are the time steps and 1024 (32x32) are flattened image pixels, in 3 channels (RGB).

I have a sequential model with an LSTM layer:

model = Sequential()
model.add(LSTM(128, input_shape=(225, 1024, 3))

But this results in the error:

Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4

The documentation mentions that the input tensor for LSTM layer should be a 3D tensor with shape (batch_size, timesteps, input_dim), but in my case my input_dim is 2D.

What is the suggested way to input a 3 channel image into an LSTM layer in Keras?

have you tried giving input_shape=X_train.shape[1:] . Assuming that X_train is your input array — Hari Krishnan
Yes, I have. X_train.shape[1:] gives me (225, 1024, 3) which is what was hard-coded as the input_shape param — shubhamsingh

Daniel Möller Daniel Möller · Accepted Answer · 2017-12-06T11:30:35

If you want the number of images to be a sequence (like a movie with frames), you need to put pixels AND channels as features:

input_shape = (225,3072)  #a 3D input where the batch size 7338 wasn't informed

If you want more processing before throwing 3072 features into an LSTM, you can combine or interleave 2D convolutions and LSTMs for a more refined model (not necessarily better, though, each application has its particular behavior).

You can also try to use the new ConvLSTM2D, which will take the five dimensional input:

input_shape=(225,32,32,3) #a 5D input where the batch size 7338 wasn't informed

I'd probably create a convolutional net with several TimeDistributed(Conv2D(...)) and TimeDistributed(MaxPooling2D(...)) before adding a TimeDistributed(Flatten()) and finally the LSTM(). This will very probably improve both your image understanding and the performance of the LSTM.

python - Keras - Input a 3 channel image into LSTM

2 Answers