Closed spatodia closed 4 years ago
Hello folks,
Beginners question.. how does the Imagenet synthetic dataset used for training in the default case get generated? I see the4 training pipeline uses 1281167 images + 50000 validation images.
It's randomly generated using tf.truncated_normal. You can see the code here:
tf.truncated_normal
https://github.com/tensorflow/benchmarks/blob/c55b4aac7861b3c519803d207045c045c9440c4d/scripts/tf_cnn_benchmarks/models/model.py#L243-L261
Hello folks,
Beginners question.. how does the Imagenet synthetic dataset used for training in the default case get generated? I see the4 training pipeline uses 1281167 images + 50000 validation images.