FrankCAN

Thread Issue

1

Hi, thanks for your tensorflow version code. I just wonder why you use Thread method to load dataset, rather than load all the data in one time. Thanks for your...

CUDA_ERROR_ILLEGAL_ADDRESS Issue

2

Hi, Is there anyone who meets the CUDA problem as below: E tensorflow/stream_executor/cuda/cuda_event.cc:49] Error polling for event status: failed to query event: CUDA_ERROR_ILLEGAL_ADDRESS F tensorflow/core/common_runtime/gpu/gpu_event_mgr.cc:203] Unexpected Event status: 1 Many...

broadcasting issue

4

Hi Petar, Many thanks for your code. For the f_1 to transpose(f_2) operation, can I change the f_2 to f_2_neighbor (BxNxKx1) which means that obtain all the k neighbors first...

Hi, how could I only use the image or the point cloud for tracking, I tried to disable the fusion mode in config file, but it has an error that...

velodyne_reduced path issue

2

Hi, thanks for sharing your great work, but I got a problem when I use rrc detector to train the model, the error is as below: Det ratio 1.5 Only...

pedestrian config

2

Hi, thanks for your great work, but could you please share your pedestrian config for training, as I only got 42.22 % 35.14 % 32.92% accuracy. I just wonder how...

FPS method issue in your code

2

Hi, thanks for your impressive work. I noticed in your code that you use "FS" method for FPS downsampling in Layer 2, but why did you separate and use "F-FPS,...

Out of Memory

10

Hi, many thanks for your source, very helpful. But when I run the train.py, there is out of memory issue as below: ResourceExhaustedError (see above for traceback): OOM when allocating...

plane data generation

3

Hi, can you please introduce your plane estimation algorithm? Because I found that the testing accuracy for my own data dropped significantly, and also the accuracy varies when I change...

@kujason Dear Kujason, I trained the model and got about 88% accuracy, but I got the problem that I made up some data by copying one frame data for 10...