supervised baseline was intialized with weight = None or "Imagenet"

[aynesss]

I would like to know, to compare result of SimCLR with result of supervised (baseline), I must initialised weights of ResNet50 with None or Imagenet base = tf.keras.applications.ResNet50(weights=None, include_top=False, input_tensor=tf.keras.Input(shape=(224, 224, 3)))

OR

base = tf.keras.applications.ResNet50(weights="Imagenet", include_top=False, input_tensor=tf.keras.Input(shape=(224, 224, 3)))

[chentingpc]

We also provided supervised ResNet weights in gs://simclr-checkpoints/simclrv2/supervised

[aynesss]

Thanks but I use another network and other dataset , just I would like to know Thanks for help and if you can reply me