Launch Tensorflow-V3 Re-Collect Multiple Layers

Question

I have successfully retrained the entry-level classification of V3 using the Python2.7 api for my own 100 classes and it gives decent results, but not exceptionally well.

I also have code to redirect the entire network from scratch, as indicated here (google code) , but this is a resource and time, and I have 400,000 images, so I don’t know what accuracy will be after training.

I was wondering if I can reinstall some of the last few fully related layers or more than just a classification layer so that the accuracy can be improved to some degree, and it is also not very difficult in terms of resources and time.

I tried to search a lot, but could not find anything. Perhaps what I want to do? and I need help with this.

Answer 1

Optimizers look at the list of "learning variables." A reference to this array is available using tf.get_collection_ref(tf.GraphKeys.TRAINABLE_VARIABLES) . You should be able to change this. The reading version is tf.trainable_variables .

Please note that a step forward (withdrawal) should always be carried out, so you have to pay this cost. If you do not want this, the easiest way is to perform the output, save the output in tf records, and then train from these pre-processed data samples.