sammy-su

We tried to extract the audio data, and it turns out that the difference between full_scale and clip is not neglectable. For example, when I compare the following audio segments...

1. Yes, the audio from the full_scale video is based on the parent time. I actually manually check the audio and couldn't tell their difference. 2. I first extract the...

The SphConv specific prototxt files are generated using bin/generate_proto.py. For the prototxt for the original VGG model, please refer to the Faster R-CNN caffe implementation.

Hi, please find the weights and models at our project webpage http://sammy-su.github.io/projects/ktn/ I will update the Readme later.

The structure of DATA_DIR is DATA_DIR train.txt valid.txt pixel/ imagenet1_1/ ... {src_cnn}{layer}/ Each line in train.txt and valid.txt contains an image name, and the loader will try to read pixel/{image_name}.jpg...

1. Yes, the images are in equirectangular projection with 640 x 320 resolution. 2. Yes, we use exactly the same data in Spherical-Convolution and KernelTransformerNetwork.

Please try the new link at http://vision.cs.utexas.edu/projects/ktn/ktn.tar.gz On Wed, Jan 8, 2020 at 10:32 PM tjinjin95 wrote: > [image: image] > > Hi, would you provide other download address, it...

Because the total data size is about 4TB, it is hard to share the data under DATA_DIR. The data is generated using the script in Spherical-Convolution. Please refer to the...