Running end-to-end-lane follower on TPU

dctian / DeepPiCar

Deep Learning Autonomous Car based on Raspberry Pi, SunFounder PiCar-V Kit, TensorFlow, and Google's EdgeTPU Co-Processor

GNU General Public License v3.0

400 stars 271 forks source link

Running end-to-end-lane follower on TPU #5

Closed patrickpoirier51 closed 4 years ago

patrickpoirier51 commented 4 years ago

Hello, I am interesting to build and experiment, but I am missing a step....

You are training with Nvidia Model and generate a h5 file. Then you run the follower script using this file : lane_navigation.h5

Question: I there a supplemental step I am missing to get this KERAS file running with TPU ?

dctian commented 4 years ago

Nvidia Lane navigation model is not a very deep network, so the keras h5 model file can run on Pi CPU very quickly, at least 20-30 Frames per second. However, the traffic sign detection model (MobileNet V2 with SSD) is a very deep network, and needs to run on the TPU. Please refer to Part 6 of DeepPiCar blog on how to do traffic sign detection. Hope this help!