MOT

[./build/examples/yolo/yolo_detect models/pelee/deploy.prototxt models/pelee/pelee_SSD_304x304_iter_20000.caffemodel -detect_mode 1 -cpu_mode gpu -file_type video -indir data/bdd100k -ext mov -wait_time 1 -mean_value 1.751,1.983,2.10 -normalize_value 0.017 -confidence_threshold 0.3 -seg_resize_scales 4 -seg_label_map data/bdd100k/labelmap.prototxt](url) 你好@eric612, 我根据你的脚本train_pelee_ssd_bdd100k.sh训练啦我自己的模型。我现在想要使用这个demo_pelee_bdd100k.sh脚本来验证我的模型，可是我不知道把所需要的验证数据（图片或者视频）放在哪个文件夹呢，希望得到你的帮助，谢谢。

make error

10

@eric612 when I make the project, and it has two error: `/home/snow/MobileNet-YOLO-master/src/caffe/util/io.cpp: In function ‘bool caffe::ReadJSONToAnnotatedDatum(const string&, int, int, caffe::AnnotatedDatum*)’: /home/snow/MobileNet-YOLO-master/src/caffe/util/io.cpp:525:17: warning: unused variable ‘anno’ [-Wunused-variable] Annotation* anno = NULL;...

@eric612 When I make the project, and has error: `/usr/local/lib/libopencv_imgcodecs.so.3.4.5：对‘TIFFOpen@LIBTIFF_4.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_CTX_load_verify_locations@OPENSSL_1.0.0’未定义的引用 /usr/local/lib/libopencv_imgcodecs.so.3.4.5：对‘TIFFReadEncodedStrip@LIBTIFF_4.0’未定义的引用 /usr/local/lib/libopencv_imgcodecs.so.3.4.5：对‘TIFFSetField@LIBTIFF_4.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘ERR_clear_error@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘ENGINE_init@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_set_bio@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘ERR_reason_error_string@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_connect@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘X509_NAME_get_index_by_NID@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_CTX_ctrl@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_pending@OPENSSL_1.0.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_library_init@OPENSSL_1.0.0’未定义的引用 /usr/local/lib/libopencv_imgcodecs.so.3.4.5：对‘TIFFSetErrorHandler@LIBTIFF_4.0’未定义的引用 /usr/local/lib/libopencv_imgcodecs.so.3.4.5：对‘TIFFReadScanline@LIBTIFF_4.0’未定义的引用 //usr/lib/x86_64-linux-gnu/libpq.so.5：对‘SSL_shutdown@OPENSSL_1.0.0’未定义的引用 /usr/local/lib/libopencv_imgcodecs.so.3.4.5：对‘TIFFReadRGBAStrip@LIBTIFF_4.0’未定义的引用 collect2: error: ld returned...

Hello, I am in the training process, after the program runs the first Epoch, I cannot continue to train the second Epoch. It's stuck there and no longer runs. Please...

Hello, I would like to ask if these environmental dependencies can be configured in the Anaconda environment。

你好，我按照你的教程进行执行，前三步都比较顺利，可是我不知道第四步 Python create_list.py train train，是做什么用的，前面三步已经生成了xml文件啦。第四步我也尝试运行了一下，可是提示在 voc_label.py 文件中没有xlsx_graph，我将它删除后，重新运行，后面生成了很多文件，有.png图片，还有xml等文件，txt文件; 你可以告诉我第四步是做什么用的吗？ 谢谢

thanks your project @Robert-JunWang . I made my own model. but when I use the gen_merged_model.py. it has error: `bb@bb:~/MobileNet-YOLO/data/bdd100k/driver_map$ python gen_merged_model.py train.prototxt pelee_SSD_304x304_iter_36000.caffemodel Traceback (most recent call last): File...

hi , I want to train my own model, including target detection and lane lines. But I don't know how to train. I have collected 2000 pictures. Can you give...