UmarSpa

Run code with PyTorch 1.0

1

I have edited the instructions along with appropriate modifications, so that the code of this repo can be run with PyTorch 1.0 You can access my fork here: https://github.com/UmarSpa/CenterNet

xs, ys and preds explanation (inputs and outputs)

1

Can you please elaborate a bit about xs, ys and preds: - xs has 4 variables: - 1st of size [batchsize, 3, 511, 511] --> this is the input image...

> pos_loss=tf.reduce_sum(tf.log(pre) * tf.pow(pos_weight,2)) > neg_loss=tf.reduce_sum(tf.pow((1-gt),4)*tf.pow(neg_weight,2)*tf.log((1-pre))) tf.log(pre) in pos_loss and tf.log((1-pre) in neg_loss are wrong.

Hey, thanks for sharing the code. I am a bit confused regarding the following: https://github.com/yinboc/trans-inr/blob/f4bdc013286e2be00f9117e4e53913d6692fa49d/models/trans_inr.py#L65 So in essence, you are using Transformer Encoder output (after being passed through a FC...