Merge branch 'master' into master

.circleci/config.yml

@@ -2,13 +2,17 @@ version: 2.0
 jobs:
   build:
     docker:
-       - image: alantrrs/cuda-opencv:latest
+       - image: datamachines/cudnn_tensorflow_opencv:11.2.0_2.4.1_4.5.1-20210211
+#      - image: alexeyab84/dockerfiles:latest
+#      - image: alantrrs/cuda-opencv:latest
 #      - image: nvidia/cuda:9.0-cudnn7-devel-ubuntu16.04
     working_directory: ~/work
     steps:
       - checkout
       - run: nvcc --version
       - run: gcc --version
+      - run: export PATH=$PATH:/usr/local/include/opencv4/
+      - run: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/:/usr/lib/:/usr/lib64/
       - run: make LIBSO=1 GPU=0 CUDNN=0 OPENCV=0 -j 8
       - run: make clean
       - run: make LIBSO=1 GPU=0 CUDNN=0 OPENCV=0 DEBUG=1 -j 8

.github/ISSUE_TEMPLATE/any-other-question-or-issue.md

@@ -0,0 +1,25 @@
+---
+name: Any other question or issue
+about: Any other question or issue
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+If something doesn’t work for you, then show 2 screenshots:
+1. screenshots of your issue
+2. screenshots with such information
+```
+./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights data/dog.jpg
+ CUDA-version: 10000 (10000), cuDNN: 7.4.2, CUDNN_HALF=1, GPU count: 1
+ CUDNN_HALF=1
+ OpenCV version: 4.2.0
+ 0 : compute_capability = 750, cudnn_half = 1, GPU: GeForce RTX 2070
+net.optimized_memory = 0
+mini_batch = 1, batch = 8, time_steps = 1, train = 0
+   layer   filters  size/strd(dil)      input                output
+   0 conv     32       3 x 3/ 1    608 x 608 x   3 ->  608 x 608 x  32 0.639 BF
+```
+
+If you do not get an answer for a long time, try to find the answer among Issues with a Solved label: https://github.com/AlexeyAB/darknet/issues?q=is%3Aopen+is%3Aissue+label%3ASolved

.github/ISSUE_TEMPLATE/bug-report.md

@@ -0,0 +1,27 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+If you want to report a bug - provide:
+    * description of a bug
+    * what command do you use?
+    * do you use Win/Linux/Mac?
+    * attach screenshot of a bug with previous messages in terminal
+    * in what cases a bug occurs, and in which not?
+    * if possible, specify date/commit of Darknet that works without this bug
+    * show such screenshot with info
+```
+./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights data/dog.jpg
+ CUDA-version: 10000 (10000), cuDNN: 7.4.2, CUDNN_HALF=1, GPU count: 1
+ CUDNN_HALF=1
+ OpenCV version: 4.2.0
+ 0 : compute_capability = 750, cudnn_half = 1, GPU: GeForce RTX 2070
+net.optimized_memory = 0
+mini_batch = 1, batch = 8, time_steps = 1, train = 0
+   layer   filters  size/strd(dil)      input                output
+```

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,13 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: Feature-request
+assignees: ''
+
+---
+
+For Feature-request:
+    * describe your feature as detailed as possible
+    * provide link to the paper and/or source code if it exist
+    * attach chart/table with comparison that shows improvement

.github/ISSUE_TEMPLATE/training-issue---no-detections---nan-avg-loss---low-accuracy.md

@@ -0,0 +1,30 @@
+---
+name: Training issue - no-detections / Nan avg-loss / low accuracy
+about: Training issue - no-detections / Nan avg-loss / low accuracy
+title: ''
+labels: Training issue
+assignees: ''
+
+---
+
+If you have an issue with training - no-detections / Nan avg-loss / low accuracy:
+    * read FAQ: https://github.com/AlexeyAB/darknet/wiki/FAQ---frequently-asked-questions
+    * what command do you use?
+    * what dataset do you use?   
+    * what Loss and mAP did you get?
+    * show chart.png with Loss and mAP    
+    * check your dataset - run training with flag `-show_imgs` i.e. `./darknet detector train ... -show_imgs` and look at the `aug_...jpg` images, do you see correct truth bounded boxes?
+    * rename your cfg-file to txt-file and drag-n-drop (attach) to your message here
+    * show content of generated files `bad.list` and `bad_label.list` if they exist
+    * Read `How to train (to detect your custom objects)` and `How to improve object detection` in the Readme: https://github.com/AlexeyAB/darknet/blob/master/README.md
+    * show such screenshot with info
+```
+./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights data/dog.jpg
+ CUDA-version: 10000 (10000), cuDNN: 7.4.2, CUDNN_HALF=1, GPU count: 1
+ CUDNN_HALF=1
+ OpenCV version: 4.2.0
+ 0 : compute_capability = 750, cudnn_half = 1, GPU: GeForce RTX 2070
+net.optimized_memory = 0
+mini_batch = 1, batch = 8, time_steps = 1, train = 0
+   layer   filters  size/strd(dil)      input                output
+```