nms version for roadsign example

[davideCremona]

Hi, I'm experimenting with your repository and I've started with following the tutorial. I've successfully trained an ssd mobilenet model with the steps in readme.md, exported the frozen graph but now I want to test it on a video. To test the model I'm using your linked repository for realtime object detection. I'm confused with the nms_version. What version should I use? I'm copying the .yml file for clarity:

---
image_input: 'images'       # input image dir
movie_input: '/home/DATI/insulators/SSD_mobilenet/test_videos/route226_argentina.mp4'    # mp4 or avi. Movie file.
#camera_input: 0            # USB Webcam on PC
camera_input: 1             # USB Webcam on TX2
## Input Must be OpenCV readable
## Onboard camera on Xavier (with TX2 onboard camera)
#camera_input: "nvarguscamerasrc ! video/x-raw(memory:NVMM), width=1280, height=720,format=NV12, framerate=120/1 ! nvvidconv ! video/x-raw,format=I420 ! videoflip method=rotate-180 ! appsink"
## Onboard camera on TX2 ### (need: apt-get install libxine2)
#camera_input: "nvcamerasrc ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720, format=(string)I420, framerate=(fraction)30/1 ! nvvidconv flip-method=0 ! video/x-raw, format=(string)BGRx ! videoconvert ! video/x-raw, format=(string)BGR ! appsink"
## Onboard or external RTSP feed
#camera_input: "rtspsrc location=rtsp://127.0.0.1:8554/test latency=500 ! rtph264depay ! h264parse ! omxh264dec ! nvvidconv ! video/x-raw, width=(int)1280, height=(int)720, format=(string)BGRx ! videoconvert ! appsink"

force_gpu_compatible: False # If True with visualize False, speed up. Forces all CPU tensors to be allocated with Cuda pinned memory.
save_to_file: True         # movie or camera: ./output_movie/output_unixtime.avi. Save it in avi format to prevent compression degradation. Requires a lot of disk space.
                            # image: ./output_image/PATH_TO_FILE. Save it in image file.
visualize: True             # True: Show result image. False: Without image show.
vis_worker: False           # True: Visualization run on process. (With visuzalize:True)
max_vis_fps: 0              # >=1: Limit of show fps. 0: No limit - means try to spend full machine power for visualization. (With visualize:True.)
vis_text: True              # Display fps on result image. (With visualize:True.)
max_frames: 5000            # >=1: Quit when frames done. 0: no exit. (With visualize:False)
width: 600                  # Camera width.
height: 600                 # Camera height.
fps_interval: 5             # FPS console out interval and FPS stream length.
det_interval: 100           # interval [frames] to print detections to console
det_th: 0.5                 # detection threshold for det_intervall
worker_threads: 4           # parallel detection for Mask R-CNN.
split_model: True           # Splits Model into a GPU and CPU session for SSD/Faster R-CNN.
log_device: False           # Logs GPU / CPU device placement
allow_memory_growth: True   # limits memory allocation to the actual needs
debug_mode: False           # Show FPS spike value
split_shape: 1917           # 1917, 3000, 3309, 5118, 7326, 51150. ExpandDims_1's shape.

model_type: 'nms_v2'
model_path: '/home/DATI/insulators/SSD_mobilenet/output_models/frozen_inference_graph.pb'
label_path: '/home/davidecremona/PycharmProjects/train_ssd_mobilenet/roadsign_data/roadsign_label_map.pbtxt'
num_classes: 4

Thank you in advance, Davide.

[naisy]

Hi @davideCremona, Probably nms_v2, but if it doesn't work, analyze the model structure. About Split Model Since ssd mobilenet of realtime object detection split by non-maximum suppression, an error will occur if this structure is different.

You can also use: split_model: False this setting is slow but maybe work.

[davideCremona]

Setting split_model: False works, I'm getting around 60fps on nvidia RTX 2080, but visualizing no detections in realtime nor in the saved video, probably because it does not contain any speed_20, speed_10, speed_30 or stop.

Can you please share your test video? I will do a realtime object detection on that to see if everything works as expected. Thank you again, Davide.

[naisy]

I don't have a sample video as I only use it for real-time detection using a usb camera. Please try to see my youtube video with a usb camera. Realtime Object Detection on TX2 cd ~/github/realtime_object_detection python run_stream.py

or use train_ssd_mobilenet/roadsign_data/PascalVOC/JPEGImages data. cp -r ~/github/train_ssd_mobilenet/roadsign_data/PascalVOC/JPEGImages ~/github/realtime_object_detection/images cd ~/github/realtime_object_detection python run_image.py

[davideCremona]

Hi, I've used some code of your realtime object detection repository and it all works perfectly. Thanks for the support