i went through how tf calculate , update gradients of loss function w.r.t it's loss function in ****tf.train.optimizer.minimize(loss, global_step=none, var_list=none, gate_gradients=1, aggregation_method=none, colocate_gradients_with_ops=false, name=none, grad_loss=none**)**
so went through source code in link i'v found the main gradient function enter link description here in code don't understand why initialize gradients 1 in line 408.
Comments
Post a Comment