tf2gap8 Regression Use Case

tf2gap8 Regression Use Case2019-10-02T13:56:18+00:00

Tagged: 

Viewing 0 reply threads
  • Author
    Posts
    • Tobias DentlerTobias Dentler
      Participant
      Post count: 3

      Hi all,

      has anyone ever tried to build an example doing a regression instead of a classification task? I’m currently experimenting with adaptions of the MNIST example, but haven’t gotten a proper output.
      Most likely the GTT transforms my output layers in way I haven’t fully understand yet.

      The last layers of my architecture look like follows, with layer definitions coming from the mnist cnn.py file:

      conv3, w3, b3 = cnn.new_conv_layer(input = conv2, num_channel_input = 16 ,filter_size=(1,2), num_filter=16, pooling=True, Relu = True)
      layer_flat, num_features = cnn.flatten_layer(conv3)
      layer_fc1, w_fcl, b_fcl = cnn.new_connected_layer(input=layer_flat,num_input=num_features, num_output=1, ReLu=False)
      y_pred = layer_fc1
      y_pred_cls = tf.argmax(y_pred, dimension = 1, name=”y_output”)

      The training/testing process looks fine. However after transforming the net and flashing it on the hardware, it doesn’t perform as expected. The outputs seem to be rather arbitrary laying in the short int range instead of the expected range [0, 10].

      Are there hints on how to define the last layers before the transformation if I want to perform a regression task? Happy to share more informarion if needed.

      Thank you

Viewing 0 reply threads
  • You must be logged in to reply to this topic.