It now works. I just used this line to copy the contents of train.txt (which contains jpg paths) to test.txt (which was non-existent in the first place) !cp data/train.txt data/test.txt Then printed the result using this line: !cat data/result.txt

I tried doing this line in google colab: !./darknet detector map data/obj.data cfg/yolov3_training.cfg /content/gdrive/MyDrive/yolov3/yolov3_training_last_5_6_21.weights -dont_show -ext_output <data/test.txt> result.txt This error still shows up: /bin/bash: data/test.txt: No such file or directory

someone got RTSP working on v3, I tested it and it works pretty well however audio is not supported yet :( https://github.com/FiveLeavesLeft/WyzeCameraLiveStream

Previous link was pointing to a code.google.com repository, which reported a 404 error.

New link seems to be not official, but working ;)

Old link: https://code.google.com/archive/p/cpp-btree/ New link: https://github.com/algorithm-ninja/cpp-btree

Hi, fffaraz.

I added NCNN to Machine Learning.

Could you review & accept my changes, pls?

https://github.com/Tencent/ncnn

Best regards, Proydakov Evgeny.

Update path to reference the digit_classifier directory instead of the image_classification directory.

I have a v3 with WyzeHacks installed - I would be willing to try out any builds for RTSP support. Thanks

The issue:

/usr/bin/ld: warning: libnvidia-fatbinaryloader.so.440.18, needed by /usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so, not found (try using -rpath or -rpath-link)
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Finish'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_symbol_name'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_string_at_offset'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_GetCandidate'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_Delete'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf_size'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_section_contents'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Load_Host_Object'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Delete'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Add_Cubin'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_file_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_PickCandidate'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_section_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `gpuInfoRunsOn'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_GetIdentifier'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_symbol_name'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Free_Fatbinary'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `gpucompSetLogLine'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_SetBinary'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_shnum'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_section_name'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Get_FatBinary_From_Object'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_symbol_shndx'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_file_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_section_name'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_SetPtxasOptions'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_SetTargetSM'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_CreateHandle'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Next_Library_Member'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_typed_section_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Start'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Free_Host_Object'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_string_at_offset'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf_end'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_HasDebug'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_shnum'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_named_section_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_symbol_shndx'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf32_section_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf_is_64bit'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_GetPtxasOptions'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Start_Reading_Library'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_typed_section_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elf64_named_section_header'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_Compile'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `gpucompRestoreLogLine'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `fatBinaryCtl_SetPolicy'
/usr/lib/gcc/aarch64-linux-gnu/7/../../../aarch64-linux-gnu/libcuda.so: undefined reference to `elfLink_Finish_Reading_Library'
collect2: error: ld returned 1 exit status
Makefile:176: recipe for target 'darknet' failed
make: *** [darknet] Error 1
make: *** Waiting for unfinished jobs....
src/yolo_v2_class.cpp: In member function ‘std::vector<bbox_t> Detector::tracking_id(std::vector<bbox_t>, bool, int, int)’:
src/yolo_v2_class.cpp:370:40: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
         if (prev_bbox_vec_deque.size() > frames_story) prev_bbox_vec_deque.pop_back();
             ~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~
src/yolo_v2_class.cpp:385:34: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
                     if (cur_dist < max_dist && (k.track_id == 0 || dist_vec[m] > cur_dist)) {
                         ~~~~~~~~~^~~~~~~~~~
src/yolo_v2_class.cpp:409:40: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
         if (prev_bbox_vec_deque.size() > frames_story) prev_bbox_vec_deque.pop_back();
             ~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~
The command '/bin/sh -c make  GPU=1 CUDNN=1 CUDNN_HALF=1 OPENCV=0 LIBSO=1  ARCH="-gencode arch=compute_72,code=[sm_72,compute_72]" -j $(nproc)' returned a non-zero code: 2

Dockerfile:

FROM nvcr.io/nvidia/l4t-tensorflow:r32.5.0-tf2.3-py3
ARG DEBIAN_FRONTEND=noninteractive

ENV EVERCAM_ANALYTICS_PATH='/gate_app'
ENV LANG en_US.UTF-8 
RUN  export LC_ALL=C.UTF-8
RUN mkdir /gate_app

RUN apt-get update -y

RUN apt-get -y install gstreamer1.0-tools gstreamer1.0-alsa gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav
RUN apt-get -y install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-good1.0-dev libgstreamer-plugins-bad1.0-dev
RUN apt-get install -y   postgresql-client python3-opencv make  cifs-utils  curl libpq-dev git pkg-config

RUN export LC_ALL=C.UTF-8

RUN pip3 install --upgrade pip

RUN pip3 install  filterpy Shapely psycopg2  boto3   pytz  requests scikit-image

RUN apt-get install -y python3-sklearn libopencv-dev

RUN git clone --recursive https://github.com/skvark/opencv-python.git
WORKDIR  opencv-python
RUN export CMAKE_ARGS="WITH_GSTREAMER=ON"

RUN pip3 wheel . --verbose
RUN pip3 install opencv_python*.whl


RUN rm /usr/bin/python && \
    ln -s /usr/bin/python3 /usr/bin/python && \
    ln -s /usr/bin/pip3 /usr/bin/pip
#RUN pip3 install vidstab[cv2]

RUN /usr/bin/env
RUN git clone https://github.com/AlexeyAB/darknet
WORKDIR darknet
RUN make  GPU=1 CUDNN=1 CUDNN_HALF=1 OPENCV=0 LIBSO=1  ARCH="-gencode arch=compute_72,code=[sm_72,compute_72]" -j $(nproc)

@berinhard For me, clearing the cache in the system and then running again did the trick. How much is the GPU utilisation while running the inference?

You'll have to mount your Google Drive in the colab notebook to use it. from google.colab import drive drive.mount('/content/gdrive')

You'll have to give the path you want to use

Hi, I believe this was added in a fork located here:

The developer mentioned it increases detection 3x ect.

https://github.com/AlexeyAB/darknet

Hello, would you please tell me where should I to find the implementation. I can't find relative information.

Confirmed this fixed my problem with my wyze cam v2 FCC ID: 2ANJHWYZEC02

• Added latest Wyze v2 RTSP firmware source
• Synced hacked rc file latest Wyze v2 RTSP firmware
• Matched blocksize for wyzev2 to match latest RTSP firmware
• Added updated cfw for latest Wyze v2 cameras (FCCID ending in C02)

Resolves https://github.com/EliasKotlyar/Xiaomi-Dafang-Hacks/issues/1667 and https://github.com/EliasKotlyar/Xiaomi-Dafang-Hacks/issues/1702

Tested this across 3 Wyze cams no issues. Users also reported success with the updated firmware in the above issue threads

Same issue when attempting to detect a custom yolov4-tiny model

Config: CUDA-version: 11020 (11020), cuDNN: 8.1.1, CUDNN_HALF=1, GPU count: 1
OpenCV version: 4.2.0

Success!! Thanks buddy

What's the root password for the v3? wellknown does not work

WYom2020