I want to use LSTMs and RNNs for sequence classification problem. I have features extracted from video segment of 10 sec @ 30 fps i.e. total of 300 frames. For each frame I have a feature representation of d-dimensions. I have label associated for for the entire video segment. Thus, my training data looks like [((x_1_1, x_1_2, x_1_3,...,x_1_300), y_1), ((x_2_1, x_2_2, x_2_3,...,x_2_300),y_2),..] and so on. Thus, I have 1 label for sequence of 300 features, each with dimension d. I want to use LSTM/RNNs to learn these representation for sequence classification. Can someone point me in right direction? Most of the code and description on LSTM/RNN in keras I found used (feature, label) rather than (sequence, label).
closed as off-topic by Sycorax, mdewey, Peter Flom♦ Sep 16 '17 at 13:17
This question appears to be off-topic. The users who voted to close gave this specific reason:
- "This question appears to be off-topic because EITHER it is not about statistics, machine learning, data analysis, data mining, or data visualization, OR it focuses on programming, debugging, or performing routine operations within a statistical computing platform. If the latter, you could try the support links we maintain." – Sycorax, mdewey, Peter Flom