demo.py with KITTI dataset error

[yhhwangRTOS]

Hi

I trained KITTI dataset and got some ckpt files The problem is when I try to test using demo.py, there's some error like this

---

InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [21] rhs shape= [4] [[Node: save/Assign_2 = Assign[T=DT_FLOAT, _class=["loc:@cls_score/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](cls_score/biases, save/RestoreV2_2/_5)]]

I already saw faster_rcnn_kitti.yml file. In that file, NCLASSES is 4 But in the demo.py, the number of declared CLASS is 21 (like car, airplane, cat, etc...) So I changed it to 4 but it didn't work.

Is there anybody how to solve this problem...?

All I want to do is just test the image using ckpt file which trained using KITTI data set

Thanks

[woxihuanchirou]

Hi,Have you solved your problem?

[yhhwangRTOS]

yes I solved that Thx!