wrong params given to layers in squeeze_excitation
wranai opened this issue · comments
wranai commented
This here for squeeze_excitation
seems to be incorrect: s
is just getting overwritten in each line since the layers work on x
.
s = x
s = tf.keras.layers.GlobalAveragePooling2D()(s)
s = tf.keras.layers.Dense(output_filters // reduction, activation="relu")(x)
s = tf.keras.layers.Dense(output_filters, activation="sigmoid")(x)
x = tf.keras.layers.Multiply()([x, s])
Kichang Kim commented
Thanks for report. Fixed by 1f6774d