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

tsinghua-rll / VoxelNet-tensorflow

A 3D object detection system for autonomous driving.

MIT License

453 stars 123 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]) #70

Open Pruthvik-Reddy opened 4 years ago

mariya12290 commented 3 years ago

Heyx @Pruthvik-Reddy bro,

did you solve the problem?