search

raytroop / YOLOv3_tf

Try to implement YOLOv3 with TensorFlow
67 stars 20 forks source link

finetune end2end is difficulty? #8

Open rimu123 opened 6 years ago

RichardChao commented 6 years ago

@raytroop Trying to get rid of the vars_det in 

vars_det = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope="Head")
# for var in vars_det:
#     print(var)
with tf.control_dependencies(update_op):
    train_op = optimizer.minimize(loss, global_step=global_step, var_list=vars_det)

the loss increases drastically though, any clue?