Closed Steve-Tod closed 4 years ago
Sorry, I found this vector is for part segmentation.
Another question, in PyTorch version conv2d without bias is used but in TensorFlow version conv2d with bias is used. Why there is such a difference?
Sorry, I found this vector is for part segmentation.
Another question, in PyTorch version conv2d without bias is used but in TensorFlow version conv2d with bias is used. Why there is such a difference?
With batchnormalization, w/ or w/o bias doesn't make any difference.
Hi, thank you for sharing the code. In your paper, there is a categorical vector for semantic segmentation network.
However, I didn't find many descriptions of this vector in the paper or any implementation of this in the code. https://github.com/WangYueFt/dgcnn/blob/69b80a370df4125adb6ac376169de2de76a61d67/tensorflow/sem_seg/model.py#L87 Here, after the max pooling, the global feature is directly repeated and concatenated with point features.
What is this categorical vector? Is it necessary?