HOU Yuenan
HOU Yuenan
@jialeli1 @LinaShanghaitech @rttariverdi67 Hi, all. I wonder if you have successfully submitted the model predictions on val/test set to the online server?
Same question. It seems that the tutorial of 3D semantic segmentation has many flaws and syntax errors.
@alexgorban @rezama Can you help us? Thanks a lot!
It needs to differentiate each lane instance to facilitate the positioning of ego-car.
I guess the steering angle is multiplied by 10.
In view_steering_model.py, you see that the angle_steers is divided by 10, which indicates what I have said above (In line 122).
If I remember it correctly, 6 lanes are (left left left, left left, left, right, right right, right right right) which follow the lane definition of CULane and facilitate the...
I see that the reward is ranging around -11 in the "Reacher" task after 20000 frames. Is it the code that achieves good performance in the "Reacher" task?
Thank you for your help. I will try again.
If you use tensorflow, then you should first build the graph and then load the pre-trained weight (tf.restore). Besides, the pre-trained model is a old checkpoint format (V1) as there...