Invalid argument Error :coordinate has shape(batch_size,K,4) while voxelwise has shape(batch_size,K,128)How can we apply scatter_nd? In FeatureNet, self.outputs = tf.scatter_nd(self.coordinate, voxelwise, [self.batch_size, 10, cfg.INPUT_HEIGHT, cfg.INPUT_WIDTH, 128]) - Githubissues

qianguih / voxelnet

This is an unofficial inplementation of VoxelNet in TensorFlow.

646 stars 241 forks source link

Invalid argument Error :coordinate has shape(batch_size,K,4) while voxelwise has shape(batch_size,K,128)How can we apply scatter_nd? In FeatureNet, self.outputs = tf.scatter_nd(self.coordinate, voxelwise, [self.batch_size, 10, cfg.INPUT_HEIGHT, cfg.INPUT_WIDTH, 128]) #86

Open Pruthvik-Reddy opened 4 years ago