Alexey

What avg-loss can you get at 2000 iteration?

So do you want? 1. Hot-key that shows/hides WxH of object near with its name 2. Show message from `1.info` file for the `1.jpg` file

@NileZhou Hi, there is no OpenCV 4.0.0 yet: https://opencv.org/releases.html

@mingxingtan Hi, please could you explain the cause of this problem?

@mingxingtan Thanks! Did you develope EfficientDet primarily for GPU or TPU? Since there are used: Grouped-convolutional layers and SE-blocks which are slow for GPU/TPU-edge. ---- So the results `32.6 AP...

@glenn-jocher In the C Darknet implementation https://github.com/AlexeyAB/darknet NMS ~ 0.0ms, but it depends on number of detected bboxes. On RTX 2070: https://github.com/AlexeyAB/darknet/issues/4497#issuecomment-564168707 `Speed: 17.2/0.3/0.4/0.0/17.9 ms - inference/[yolo]/get_network_boxes()/NMS/total per 416x416 image...

A few words why is it better to use make_safe instead constructor?

@peterdn1 Thanks! * Should we have too much files? * Can you show screenshot of detection result console/window output?

@jamessmith90 You can try to use LSTM-models f.e: https://github.com/AlexeyAB/darknet/files/3199770/yolo_v3_tiny_lstm.cfg.txt Since it uses `time_steps=16` in `yolo_v3_tiny_lstm.cfg.txt` then 1. in `train.txt` should be placed training images, by 16 consecutive images (frames) from...

Everything is the same as usual. train.txt ``` video_1_frame_1.jpg video_1_frame_2.jpg video_1_frame_3.jpg .... video_1_frame_16.jpg video_2_frame_1.jpg video_2_frame_2.jpg ... video_2_frame_16.jpg .... ``` Files `video_1_frame_1.txt` as usual https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects ``` 0 0.5 0.5 0.2 0.2...