add converter to generate yolo4 models

converters/yolo4/Dockerfile.l4t.tf15

@@ -0,0 +1,14 @@
+FROM nvcr.io/nvidia/l4t-tensorflow:r32.6.1-tf1.15-py3
+
+RUN apt-get update && apt-get install -y git sudo
+RUN git clone https://github.com/jkjung-avt/tensorrt_demos.git /tensorrt_demos
+
+RUN cd /tensorrt_demos/yolo && ./install_pycuda.sh
+RUN apt-get update && apt-get install -y cmake build-essential unzip
+ADD install_protobuf.sh /install_protobuf.sh
+RUN /install_protobuf.sh
+RUN pip3 install onnx==1.4.1
+RUN cd /tensorrt_demos/yolo && ./download_yolo.sh
+ADD run.sh /run.sh
+
+

converters/yolo4/README.md

@@ -0,0 +1,45 @@
+Following the https://github.com/jkjung-avt/tensorrt_demos#demo-5-yolov4
+
+
+A build.sh file will convert pre-trained yolov3 and yolov4 models through ONNX to TensorRT engines. The implementation with a "yolo_layer" plugin has been updated to speed up inference time of the yolov3/yolov4 models.
+
+Current "yolo_layer" plugin implementation is based on TensorRT's IPluginV2IOExt. It only works for TensorRT 6+. "yolo_layer" developed plugin by referencing similar plugin code by wang-xinyu and dongfangduoshou123. So big thanks to both of them.
+
+
+Output will be copied to the ./model folder
+
+
+
+## Available models
+
+   | TensorRT engine         | mAP @<br>IoU=0.5:0.95 |  mAP @<br>IoU=0.5  | FPS on Nano |
+   |:------------------------|:---------------------:|:------------------:|:-----------:|
+   | yolov3-tiny-288 (FP16)  |         0.077         |        0.158       |     35.8    |
+   | yolov3-tiny-416 (FP16)  |         0.096         |        0.202       |     25.5    |
+   | yolov3-288 (FP16)       |         0.331         |        0.601       |     8.16    |
+   | yolov3-416 (FP16)       |         0.373         |        0.664       |     4.93    |
+   | yolov3-608 (FP16)       |         0.376         |        0.665       |     2.53    |
+   | yolov3-spp-288 (FP16)   |         0.339         |        0.594       |     8.16    |
+   | yolov3-spp-416 (FP16)   |         0.391         |        0.664       |     4.82    |
+   | yolov3-spp-608 (FP16)   |         0.410         |        0.685       |     2.49    |
+   | yolov4-tiny-288 (FP16)  |         0.179         |        0.344       |     36.6    |
+   | yolov4-tiny-416 (FP16)  |         0.196         |        0.387       |     25.5    |
+   | yolov4-288 (FP16)       |         0.376         |        0.591       |     7.93    |
+   | yolov4-416 (FP16)       |         0.459         |        0.700       |     4.62    |
+   | yolov4-608 (FP16)       |         0.488         |        0.736       |     2.35    |
+   | yolov4-csp-256 (FP16)   |         0.336         |        0.502       |     12.8    |
+   | yolov4-csp-512 (FP16)   |         0.436         |        0.630       |     4.26    |
+   | yolov4x-mish-320 (FP16) |         0.400         |        0.581       |     4.79    |
+   | yolov4x-mish-640 (FP16) |         0.470         |        0.668       |     1.46    |
+
+
+Please update frigate/converters/yolo4/assets/run.sh to add necessary models
+
+Note:
+
+This will consume pretty significant amound of memory. You might consider extending swap on Jetson Nano
+
+Usage:
+
+cd ./frigate/converters/yolo4/
+./build.sh

converters/yolo4/assets/install_protobuf.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+set -e
+
+folder=${HOME}/src
+mkdir -p $folder
+
+echo "** Install requirements"
+sudo apt-get install -y autoconf libtool
+
+echo "** Download protobuf-3.8.0 sources"
+cd $folder
+if [ ! -f protobuf-python-3.8.0.zip ]; then
+  wget https://github.com/protocolbuffers/protobuf/releases/download/v3.8.0/protobuf-python-3.8.0.zip
+fi
+if [ ! -f protoc-3.8.0-linux-aarch_64.zip ]; then
+  wget https://github.com/protocolbuffers/protobuf/releases/download/v3.8.0/protoc-3.8.0-linux-aarch_64.zip
+fi
+
+echo "** Install protoc"
+unzip protobuf-python-3.8.0.zip
+unzip protoc-3.8.0-linux-aarch_64.zip -d protoc-3.8.0
+sudo cp protoc-3.8.0/bin/protoc /usr/local/bin/protoc
+
+echo "** Build and install protobuf-3.8.0 libraries"
+export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=cpp
+cd protobuf-3.8.0/
+./autogen.sh
+./configure --prefix=/usr/local
+make -j$(nproc)
+make check
+sudo make install
+sudo ldconfig
+
+echo "** Update python3 protobuf module"
+# remove previous installation of python3 protobuf module
+sudo apt-get install -y python3-pip
+sudo pip3 uninstall -y protobuf
+sudo pip3 install Cython
+cd python/
+python3 setup.py build --cpp_implementation
+python3 setup.py test --cpp_implementation
+sudo python3 setup.py install --cpp_implementation
+
+echo "** Build protobuf-3.8.0 successfully"

converters/yolo4/assets/run.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+
+set -xe
+cd /tensorrt_demos/plugins && make
+
+cd /tensorrt_demos/yolo
+for model in yolov4-tiny-288 \
+             yolov4-tiny-416 \
+             yolov4-288 \
+             yolov4-416 ; do
+    python3 yolo_to_onnx.py -m ${model}
+    python3 onnx_to_tensorrt.py -m ${model}
+    cp /tensorrt_demos/yolo/${model}.trt /model/${model}.trt
+done     

converters/yolo4/build.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+mkdir -p $(pwd)/model
+
+docker build --tag models.yolo4  --file ./Dockerfile.l4t.tf15 ./assets/
+
+sudo docker run --rm -it --name models.yolo4 \
+    --mount type=tmpfs,target=/tmp/cache,tmpfs-size=1000000000 \
+    -v $(pwd)/model:/model:rw \
+    -v /tmp/argus_socket:/tmp/argus_socket \
+    -e NVIDIA_VISIBLE_DEVICES=all \
+    -e NVIDIA_DRIVER_CAPABILITIES=compute,utility,video \
+    --runtime=nvidia \
+    --privileged \
+    models.yolo4 /run.sh