Taehoon Lee

Recently, I have updated the performance table to follow the recent report format. I reviewed 10 recent papers as follows, and found that error rates and 10-crop testing are no...

All the models in **TensorNets** return a softmax `tf.Tensor`, while the models in `tensorflow/models` (also backbone of `tensorflow/hub`) do a logits `tf.Tensor` (the values before softmax). That is because most...

**TensorNets** provides a seamless integration with regular TensorFlow APIs. You can define any models under `tf.variable_scope` and `tf.name_scope` to couple the model with your established scripts. This document shows basic...

The 2x down-sampling is one of the important operations in reference models. But, a convolution or a pooling with `stride=2, padding='SAME'` may result in different outputs over different deep learning...