BT123 opened this issue 7 years ago · 1 comments
The paper of NVIDIA about self-driving introduce the model you use, but the input layer is 200*66.
In your model, the size of input tensor is 100*100.
Which one is the right size in real world?
Thank you~~~
Hi @BT123 20066 should be the official one. But I believe there is no uniformly right size ;-) We found 100100 also works well.