Open ghost opened 3 years ago
Hi and thanks for this awesome repo.
I just checked the original TensorFlow implementation and found a part different from them. In the original implementation. There is a probability of applying and not applying the augmentation. But I did not find it in this repo.
The link for TensorFlow version: https://github.com/tensorflow/tpu/blob/5144289ba9c9e5b1e55cc118b69fe62dd868657c/models/official/efficientnet/autoaugment.py#L532
Original: with tf.name_scope('randauglayer{}'.format(layer_num)): for (i, op_name) in enumerate(available_ops): prob = tf.randomuniform([], minval=0.2, maxval=0.8, dtype=tf.float32) func, , args = _parse_policy_info(op_name, prob, random_magnitude, replace_value, augmentation_hparams)
this repo: ops = random.choices(self.augment_list, k=self.n)
for op, minval, maxval in ops: val = (float(self.m) / 30) * float(maxval - minval) + minval img = op(img, val)
May I ask is there any reason for this? Or is there any part I missing?
Thanks in advance
In addition, the Identity operation is not included
Hi and thanks for this awesome repo.
I just checked the original TensorFlow implementation and found a part different from them. In the original implementation. There is a probability of applying and not applying the augmentation. But I did not find it in this repo.
The link for TensorFlow version: https://github.com/tensorflow/tpu/blob/5144289ba9c9e5b1e55cc118b69fe62dd868657c/models/official/efficientnet/autoaugment.py#L532
Original: with tf.name_scope('randauglayer{}'.format(layer_num)): for (i, op_name) in enumerate(available_ops): prob = tf.randomuniform([], minval=0.2, maxval=0.8, dtype=tf.float32) func, , args = _parse_policy_info(op_name, prob, random_magnitude, replace_value, augmentation_hparams)
this repo: ops = random.choices(self.augment_list, k=self.n)
print (ops)
May I ask is there any reason for this? Or is there any part I missing?
Thanks in advance