Open NicolasMICAUX opened 3 years ago
Hello, When migrating your code from TF1 to TF2, I cannot figure out what some parameters for batch_normalization (in resnet.py, line 153) are : decay=0.9, updates_collections=None, scope=scope
decay=0.9, updates_collections=None, scope=scope
My research gave me the following results :
here is my (working) code without those parameters using TF2 :
def batch_norm(x, is_training=True, scope='batch_norm'): return tf_keras.layers.BatchNormalization(epsilon=1e-05, center=True, scale=True)(x, training=is_training)
Thx a lot,
Hello, When migrating your code from TF1 to TF2, I cannot figure out what some parameters for batch_normalization (in resnet.py, line 153) are :
decay=0.9, updates_collections=None, scope=scope
My research gave me the following results :
here is my (working) code without those parameters using TF2 :
Thx a lot,