Hello, I found a performance issue in the definition of pre_process_binary_cross_entropy, DexiNed-TF2/model.py, tf.cast(y, dtype=tf.float32) will be created repeatedly during program execution, resulting in reduced efficiency. I think it should be created before the loop.
Hello, I found a performance issue in the
definition of pre_process_binary_cross_entropy
, DexiNed-TF2/model.py,tf.cast(y, dtype=tf.float32)
will be created repeatedly during program execution, resulting in reduced efficiency. I think it should be created before the loop.The same issues exist in:
tf.dtypes.cast(tmp_y > 0., tf.float32
)tf.math.reduce_sum(mask, axis=[1, 2, 3], keepdims=True)
tf.where(tf.equal(y, 0.0), beta, beta2)
Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.