Ozora Ogino

Hi all, I'm Ozora. I'm a master student on computer science in Tokyo. I started to translate this awesome project to Japanese. Thank you.

@Mozuha @lftu119 @jimbobbennett I created new PR for translation of `README.md`. Could anyone review this? #348

Hi @almoghitelman , Here is my solution, ``` class DNN(tf.keras.models.Model): def __init__(self, num_classes=10): super(DNN, self).__init__() weight_decay = 1e-4 self.layer_1 = tf.keras.layers.Dense(32, activation='relu') self.layer_2 = tf.keras.layers.Dense(10) self.out = ArcFace(n_classes=num_classes, regularizer=regularizers.l2(weight_decay)) def...

I implemented my own ArcFace. https://github.com/ozora-ogino/asoftmax-tf This works correctly and I believe this can solve your problem.

Hi @farhantandia, Here is my DNN implementation with ASoftmax ``` class DNN(tf.keras.models.Model): def __init__(self, num_classes=10): super(DNN, self).__init__() weight_decay = 1e-4 self.layer_1 = tf.keras.layers.Dense(32, activation='relu') self.layer_2 = tf.keras.layers.Dense(10) self.out = ArcFace(n_classes=num_classes,...

I implemented my own ArcFace. https://github.com/ozora-ogino/asoftmax-tf This works correctly and I believe this can solve your problem.

@ShivaThe I added after this line and error solved. https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/master/dataset.py#L140

@ysozer This Client API seems like what you want. You can check completion by run_id. https://kubeflow-pipelines.readthedocs.io/en/latest/source/kfp.client.html#kfp.Client.wait_for_run_completion Or you can use `get_run` and write your own script with `while` statement. https://kubeflow-pipelines.readthedocs.io/en/latest/source/kfp.client.html#kfp.Client.get_run