search

kwotsin / transfer_learning_tutorial

A guide to transfer learning with inception-resnet-v2.
232 stars 80 forks source link

loss #15

Closed abbasrazaali closed 6 years ago

abbasrazaali commented 6 years ago

hi, are you using loss, it isn't used after declaration ? loss = tf.losses.softmax_cross_entropy(onehot_labels = one_hot_labels, logits = logits)

kwotsin commented 6 years ago

If the code is not using any loss, the model cannot be trained in the conventional sense. could you explain what you mean by "after declaration"?

kwotsin commented 6 years ago

Closing due to inactivity.