search

nilboy / tensorflow-yolo

tensorflow implementation of 'YOLO : Real-Time Object Detection'(train and test)
774 stars 312 forks source link

All variables are trainable even "train" was set to False ? #4

Closed JindongJiang closed 7 years ago

JindongJiang commented 7 years ago

It seems that all variables on the graph are trainable because the "train" arg of "_variable_on_cpu" was not sent to "trainable" arg of tf.get_variable. So every time we run train_op, all variable will be updated. Is that correct ?