search

somewacko / deep-features-video

Scripts to extract CNN features from video frames with Keras.
MIT License
24 stars 12 forks source link

layer #1

Open mynameisvinn opened 6 years ago

mynameisvinn commented 6 years ago

according to this: features = model.predict(frames_arr, batch_size=batch_size), you are extracting the output layer as feature representations. (in which case, thats incorrect: as youd want the last fully connected layer - that is, the layer preceding the output layer [1].)

[1] [Real-time Convolutional Neural Networks for Emotion and Gender Classification

Wazaki-Ou commented 6 years ago

@mynameisvinn I'm not an expert (in fact, I just got the code today) but I think this line in the code here makes sure it does not extract the output layer:

    # Get outputs of model from layer just before softmax predictions

    from keras.models import Model
    model = Model(model.inputs, output=model.layers[-2].output)