Difference between revisions of "Jetson/L4T/TRT Customized Example"

From eLinux.org
< Jetson‎ | L4T
Jump to: navigation, search
Line 310: Line 310:
  
 
https://forums.developer.nvidia.com/t/deepstream-sdk-vpi-on-jetson-tx2/166834/20
 
https://forums.developer.nvidia.com/t/deepstream-sdk-vpi-on-jetson-tx2/166834/20
 +
 +
 +
== Installation Steps ==
 +
=== Darknet with cuDNN-8 Support ===
 +
Below are the steps to build ''darknet'' with cuDNN-8 support.
 +
 +
Verified environment:
 +
* JetPack4.5.1 + Xavier
 +
 +
'''1. Get source'''
 +
$ git clone https://github.com/pjreddie/darknet.git
 +
$ cd darknet/
 +
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/script/topics/0001-fix-for-cudnn_v8-limited-memory-to-default-darknet-s.patch
 +
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/opencv-darknet.patch -O opencv-darknet.patch
 +
$ git am 0001-fix-for-cudnn_v8-limited-memory-to-default-darknet-s.patch
 +
$ git am opencv-darknet.patch
 +
 +
'''2. Update Makefile based on your device'''
 +
<syntaxhighlight lang="bash">
 +
GPU=1
 +
CUDNN=1
 +
OPENCV=1
 +
</syntaxhighlight>
 +
 +
*Xavier & XavierNX:
 +
<syntaxhighlight lang="bash">
 +
ARCH= -gencode arch=compute_72,code=sm_72 \
 +
      -gencode arch=compute_72,code=[sm_72,compute_72]
 +
</syntaxhighlight>
 +
 +
* TX2:
 +
<syntaxhighlight lang="bash">
 +
ARCH= -gencode arch=compute_62,code=sm_62 \
 +
      -gencode arch=compute_62,code=[sm_62,compute_62]
 +
</syntaxhighlight>
 +
 +
* Nano:
 +
<syntaxhighlight lang="bash">
 +
ARCH= -gencode arch=compute_53,code=sm_53 \
 +
      -gencode arch=compute_53,code=[sm_53,compute_53]
 +
</syntaxhighlight>
 +
 +
'''3. Build and Test'''
 +
$ make -j8
 +
$ wget https://pjreddie.com/media/files/yolov3-tiny.weights
 +
$ ./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights [video]
 +
 +
 +
=== TensorRT Python Bindings ===
 +
Below are the steps to build TensorRT Python 3.9 bindings.
 +
 +
Verified environment:
 +
* JetPack4.6 + Xavier
 +
 +
'''1. Building python3.9'''
 +
$ sudo apt install zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libreadline-dev libffi-dev libsqlite3-dev libbz2-dev
 +
$ wget https://www.python.org/ftp/python/3.9.1/Python-3.9.1.tar.xz
 +
$ tar xvf Python-3.9.1.tar.xz Python-3.9.1/
 +
 +
$ mkdir build-python-3.9.1
 +
$ cd build-python-3.9.1/
 +
$ ../Python-3.9.1/configure --enable-optimizations
 +
$ make -j $(nproc)
 +
$ sudo -H make altinstall
 +
$ cd ../
 +
 +
'''2. Build cmake 3.13.5'''
 +
$ sudo apt-get install -y protobuf-compiler libprotobuf-dev openssl libssl-dev libcurl4-openssl-dev
 +
$ wget https://github.com/Kitware/CMake/releases/download/v3.13.5/cmake-3.13.5.tar.gz
 +
$ tar xvf cmake-3.13.5.tar.gz
 +
$ rm cmake-3.13.5.tar.gz
 +
 +
$ cd cmake-3.13.5/
 +
$ ./bootstrap --system-curl
 +
$ make -j$(nproc)
 +
 +
$ echo 'export PATH='${PWD}'/bin/:$PATH' >> ~/.bashrc
 +
$ source ~/.bashrc
 +
$ cd ../
 +
 +
'''3. Prepare header'''
 +
$ mkdir python3.9
 +
$ mkdir python3.9/include
 +
$ wget http://ftp.us.debian.org/debian/pool/main/p/python3.9/libpython3.9-dev_3.9.9-2_arm64.deb
 +
$ ar x libpython3.9-dev_3.9.9-2_arm64.deb
 +
$ tar -xvf data.tar.xz
 +
$ cp ./usr/include/aarch64-linux-gnu/python3.9/pyconfig.h python3.9/include/
 +
$ cp -r Python-3.9.1/Include/* python3.9/include/
 +
 +
'''4. Build TensorRT pybinding'''
 +
$ git clone https://github.com/pybind/pybind11.git
 +
$ git clone -b release/8.0 https://github.com/NVIDIA/TensorRT.git
 +
$ cd TensorRT
 +
$ git submodule update --init --recursive
 +
 +
$ cd python/
 +
$ TRT_OSSPATH=${PWD}/.. EXT_PATH=${PWD}/../.. TARGET=aarch64 PYTHON_MINOR_VERSION=9 ./build.sh
 +
$ python3.9 -m pip install build/dist/tensorrt-8.0.1.6-cp39-none-linux_aarch64.whl
 +
 +
 +
=== Caffe ===
 +
Below are the steps to build the Caffe library.
 +
 +
Verified environment:
 +
* JetPack4.6 + Xavier
 +
 +
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/install_caffe_jp46.sh -O install_caffe_jp46.sh
 +
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/0001-patch-for-jp4.6.patch -O 0001-patch-for-jp4.6.patch
 +
$ ./install_caffe_jp46.sh
 +
$ source ~/.bashrc
 +
 +
 +
=== MXNet ===
 +
Below are the steps to build the MXNet 1.8.0 library.
 +
 +
Verified environment:
 +
* JetPack4.5.1 + Xavier
 +
 +
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/mxnet_v1.8.x.patch -O mxnet_v1.8.x.patch
 +
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/autobuild_mxnet.sh -O autobuild_mxnet.sh
 +
$ sudo chmod +x autobuild_mxnet.sh
 +
$ ./autobuild_mxnet.sh Xavier
 +
$ cd mxnet/build/
 +
$ pip3 install mxnet-1.8.0-py3-none-any.whl
 +
 +
 +
== Common Error ==
 +
=== "Unsupported ONNX data type: UINT8 (2)" ===
 +
This error is from TensorRT. The root cause is that ONNX expects the input image to be INT8 but TensorRT uses Float32.
 +
 +
To solve this issue, you can modify the input data format of ONNX with our graphsurgeon API.
 +
 +
$ sudo apt-get install python3-pip libprotobuf-dev protobuf-compiler
 +
$ git clone https://github.com/NVIDIA/TensorRT.git
 +
$ cd TensorRT/tools/onnx-graphsurgeon/
 +
$ make install
 +
 +
<syntaxhighlight lang="python">
 +
import onnx_graphsurgeon as gs
 +
import onnx
 +
import numpy as np
 +
 +
graph = gs.import_onnx(onnx.load("model.onnx"))
 +
for inp in graph.inputs:
 +
    inp.dtype = np.float32
 +
 +
onnx.save(gs.export_onnx(graph), "updated_model.onnx")
 +
</syntaxhighlight>
 +
 +
 +
=== "Illegal instruction (core dumped)" ===
 +
This is a known issue in NumPy v1.19.5.
 +
 +
To solve this issue, you can either downgrade your NumPy into 1.19.4 or manually update an environment variable.
 +
 +
* Downgrade NumPy
 +
$ sudo apt-get install python3-pip
 +
$ pip3 install Cython
 +
$ pip3 install numpy==1.19.4
 +
 +
* Update environment variable
 +
$ export OPENBLAS_CORETYPE=ARMV8

Revision as of 07:22, 23 December 2021

This page collects information to deploy customized models with TensorRT and some common questions for Jetson.

TensorRT Python

OpenCV with ONNX model

Below is an example to deploy TensorRT from an ONNX model with OpenCV images.

Verified environment:

  • JetPack4.5.1 + Xavier
import cv2
import time
import numpy as np
import tensorrt as trt
import pycuda.autoinit
import pycuda.driver as cuda

EXPLICIT_BATCH = 1 << (int)(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)
TRT_LOGGER = trt.Logger(trt.Logger.INFO)
runtime = trt.Runtime(TRT_LOGGER)

host_inputs  = []
cuda_inputs  = []
host_outputs = []
cuda_outputs = []
bindings = []


def Inference(engine):
    image = cv2.imread("/usr/src/tensorrt/data/resnet50/airliner.ppm")
    image = (2.0 / 255.0) * image.transpose((2, 0, 1)) - 1.0

    np.copyto(host_inputs[0], image.ravel())
    stream = cuda.Stream()
    context = engine.create_execution_context()

    start_time = time.time()
    cuda.memcpy_htod_async(cuda_inputs[0], host_inputs[0], stream)
    context.execute_async(bindings=bindings, stream_handle=stream.handle)
    cuda.memcpy_dtoh_async(host_outputs[0], cuda_outputs[0], stream)
    stream.synchronize()
    print("execute times "+str(time.time()-start_time))

    output = host_outputs[0].reshape(np.concatenate(([1],engine.get_binding_shape(1))))
    print(np.argmax(output))


def PrepareEngine():
    with trt.Builder(TRT_LOGGER) as builder, builder.create_network(EXPLICIT_BATCH) as network, trt.OnnxParser(network, TRT_LOGGER) as parser:
        builder.max_workspace_size = 1 << 30
        with open('/usr/src/tensorrt/data/resnet50/ResNet50.onnx', 'rb') as model:
            if not parser.parse(model.read()):
                print ('ERROR: Failed to parse the ONNX file.')
                for error in range(parser.num_errors):
                    print (parser.get_error(error))
        engine = builder.build_cuda_engine(network)

        # create buffer
        for binding in engine:
            size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
            host_mem = cuda.pagelocked_empty(shape=[size],dtype=np.float32)
            cuda_mem = cuda.mem_alloc(host_mem.nbytes)

            bindings.append(int(cuda_mem))
            if engine.binding_is_input(binding):
                host_inputs.append(host_mem)
                cuda_inputs.append(cuda_mem)
            else:
                host_outputs.append(host_mem)
                cuda_outputs.append(cuda_mem)

        return engine


if __name__ == "__main__":
    engine = PrepareEngine()
    Inference(engine)


OpenCV with PLAN model

Below is an example to deploy TensorRT from a TensorRT PLAN model with OpenCV images.

Verified environment:

  • JetPack4.5.1 + Xavier
$ /usr/src/tensorrt/bin/trtexec --onnx=/usr/src/tensorrt/data/resnet50/ResNet50.onnx --saveEngine=trt.plan
import cv2
import time
import numpy as np
import tensorrt as trt
import pycuda.autoinit
import pycuda.driver as cuda

EXPLICIT_BATCH = 1 << (int)(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)
TRT_LOGGER = trt.Logger(trt.Logger.INFO)
runtime = trt.Runtime(TRT_LOGGER)

host_inputs  = []
cuda_inputs  = []
host_outputs = []
cuda_outputs = []
bindings = []


def Inference(engine):
    image = cv2.imread("/usr/src/tensorrt/data/resnet50/airliner.ppm")
    image = (2.0 / 255.0) * image.transpose((2, 0, 1)) - 1.0

    np.copyto(host_inputs[0], image.ravel())
    stream = cuda.Stream()
    context = engine.create_execution_context()

    start_time = time.time()
    cuda.memcpy_htod_async(cuda_inputs[0], host_inputs[0], stream)
    context.execute_async(bindings=bindings, stream_handle=stream.handle)
    cuda.memcpy_dtoh_async(host_outputs[0], cuda_outputs[0], stream)
    stream.synchronize()
    print("execute times "+str(time.time()-start_time))

    output = host_outputs[0].reshape(np.concatenate(([1],engine.get_binding_shape(1))))
    print(np.argmax(output))


def PrepareEngine():
    runtime = trt.Runtime(TRT_LOGGER)
    with open('./trt.plan', 'rb') as f:
        buf = f.read()
        engine = runtime.deserialize_cuda_engine(buf)

    # create buffer
    for binding in engine:
        size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
        host_mem = cuda.pagelocked_empty(shape=[size],dtype=np.float32)
        cuda_mem = cuda.mem_alloc(host_mem.nbytes)

        bindings.append(int(cuda_mem))
        if engine.binding_is_input(binding):
            host_inputs.append(host_mem)
            cuda_inputs.append(cuda_mem)
        else:
            host_outputs.append(host_mem)
            cuda_outputs.append(cuda_mem)

    return engine


if __name__ == "__main__":
    engine = PrepareEngine()
    Inference(engine)


Multi-threading

Below is an example to run TensorRT with threads.

Verified environment:

  • JetPack4.5.1 + Xavier
$ /usr/src/tensorrt/bin/trtexec --onnx=/usr/src/tensorrt/data/mnist/mnist.onnx --saveEngine=mnist.trt
$ cd /usr/src/tensorrt/data/mnist/
$ sudo pip3 install pillow
$ python3 download_pgms.py
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/my_tensorrt_code.py -O my_tensorrt_code.py
import threading
import time
from my_tensorrt_code import TRTInference, trt

exitFlag = 0

class myThread(threading.Thread):
   def __init__(self, func, args):
      threading.Thread.__init__(self)
      self.func = func
      self.args = args
   def run(self):
      print ("Starting " + self.args[0])
      self.func(*self.args)
      print ("Exiting " + self.args[0])

if __name__ == '__main__':
    # Create new threads
    '''
    format thread:
        - func: function names, function that we wished to use
        - arguments: arguments that will be used for the func's arguments
    '''

    trt_engine_path = 'mnist.trt'

    max_batch_size = 1
    trt_inference_wrapper = TRTInference(trt_engine_path,
        trt_engine_datatype=trt.DataType.FLOAT,
        batch_size=max_batch_size)

    # Get TensorRT SSD model output
    input_img_path = '/usr/src/tensorrt/data/mnist/3.pgm'

    thread1 = myThread(trt_inference_wrapper.infer, [input_img_path])

    # Start new Threads
    thread1.start()
    thread1.join()
    trt_inference_wrapper.destory();
    print ("Exiting Main Thread")


Deepstream

YoloV4 Tiny

Verified environment:

  • JetPack4.5.1 + Xavier

Deepstream can reach 60fps with 4 video stream on Xavier:

$ cd /opt/nvidia/deepstream/deepstream-5.1/sources/objectDetector_Yolo
$ wget https://raw.githubusercontent.com/AastaNV/eLinux_data/main/deepstream/yolov4-tiny/yolov4_tiny.patch
$ git apply yolov4_tiny.patch
$ export CUDA_VER=10.2
$ make -C nvdsinfer_custom_impl_Yolo
$ wget https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-tiny.cfg -q --show-progress
$ wget https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.weights -q --show-progress
$ wget https://raw.githubusercontent.com/AastaNV/eLinux_data/main/deepstream/yolov4-tiny/deepstream_app_config_yoloV4_tiny.txt
$ wget https://raw.githubusercontent.com/AastaNV/eLinux_data/main/deepstream/yolov4-tiny/config_infer_primary_yoloV4_tiny.txt
$ deepstream-app -c deepstream_app_config_yoloV4_tiny.txt


Custom Parser for SSD-MobileNet Trained by Jetson-inference

Verified environment:

  • JetPack4.5.1 + Xavier
$ cd /opt/nvidia/deepstream/deepstream-5.1/sources/objectDetector_SSD/
$ sudo wget https://raw.githubusercontent.com/AastaNV/eLinux_data/main/deepstream/ssd-jetson_inference/ssd-jetson_inference.patch
$ sudo git apply ssd-jetson_inference.patch
$ sudo CUDA_VER=10.2 make -C nvdsinfer_custom_impl_ssd/

Update config_infer_primary_ssd.txt:

Ex.

diff --git a/config_infer_primary_ssd.txt b/config_infer_primary_ssd.txt
index e5bf468..81c52fd 100644
--- a/config_infer_primary_ssd.txt
+++ b/config_infer_primary_ssd.txt
@@ -62,15 +62,13 @@ gpu-id=0
 net-scale-factor=0.0078431372
 offsets=127.5;127.5;127.5
 model-color-format=0
-model-engine-file=sample_ssd_relu6.uff_b1_gpu0_fp32.engine
-labelfile-path=ssd_coco_labels.txt
-uff-file=sample_ssd_relu6.uff
+model-engine-file=ssd-mobilenet.uff_b1_gpu0_fp16.engine
+uff-file=ssd.uff
 infer-dims=3;300;300
 uff-input-order=0
 uff-input-blob-name=Input
-batch-size=1
-## 0=FP32, 1=INT8, 2=FP16 mode
-network-mode=0
+labelfile-path=labels.txt
+network-mode=2
 num-detected-classes=91
 interval=0
 gie-unique-id=1
$ deepstream-app -c deepstream_app_config_ssd.txt


VPI

VPI with Jetson-utils

Below is an example to use VPI with jetson-utils

Verified environment:

  • JetPack4.6 + XavierNX
import numpy as np
import jetson.utils
import vpi


display = jetson.utils.glDisplay()

camera = jetson.utils.gstCamera(1920, 1280, '0')
camera.Open()

while display.IsOpen():
    frame, width, height = camera.CaptureRGBA(zeroCopy=1)
    input = vpi.asimage(np.uint8(jetson.utils.cudaToNumpy(frame)))
    with vpi.Backend.CUDA:
        output = input.convert(vpi.Format.U8) 
        output = output.box_filter(11, border=vpi.Border.ZERO).convert(vpi.Format.RGB8)
        vpi.clear_cache()

    display.RenderOnce(jetson.utils.cudaFromNumpy(output.cpu()), width, height)
    display.SetTitle("{:s} | {:d}x{:d} | {:.1f} FPS".format("Camera Viewer", width, height, display.GetFPS()))

camera.Close()


VPI with Deepstream

Please find the following link for the example:

https://forums.developer.nvidia.com/t/deepstream-sdk-vpi-on-jetson-tx2/166834/20


Installation Steps

Darknet with cuDNN-8 Support

Below are the steps to build darknet with cuDNN-8 support.

Verified environment:

  • JetPack4.5.1 + Xavier

1. Get source

$ git clone https://github.com/pjreddie/darknet.git
$ cd darknet/
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/script/topics/0001-fix-for-cudnn_v8-limited-memory-to-default-darknet-s.patch
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/opencv-darknet.patch -O opencv-darknet.patch
$ git am 0001-fix-for-cudnn_v8-limited-memory-to-default-darknet-s.patch
$ git am opencv-darknet.patch

2. Update Makefile based on your device

GPU=1
CUDNN=1
OPENCV=1
  • Xavier & XavierNX:
ARCH= -gencode arch=compute_72,code=sm_72 \
      -gencode arch=compute_72,code=[sm_72,compute_72]
  • TX2:
ARCH= -gencode arch=compute_62,code=sm_62 \
      -gencode arch=compute_62,code=[sm_62,compute_62]
  • Nano:
ARCH= -gencode arch=compute_53,code=sm_53 \
      -gencode arch=compute_53,code=[sm_53,compute_53]

3. Build and Test

$ make -j8
$ wget https://pjreddie.com/media/files/yolov3-tiny.weights
$ ./darknet detector demo cfg/coco.data cfg/yolov3-tiny.cfg yolov3-tiny.weights [video]


TensorRT Python Bindings

Below are the steps to build TensorRT Python 3.9 bindings.

Verified environment:

  • JetPack4.6 + Xavier

1. Building python3.9

$ sudo apt install zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libreadline-dev libffi-dev libsqlite3-dev libbz2-dev
$ wget https://www.python.org/ftp/python/3.9.1/Python-3.9.1.tar.xz
$ tar xvf Python-3.9.1.tar.xz Python-3.9.1/
$ mkdir build-python-3.9.1
$ cd build-python-3.9.1/
$ ../Python-3.9.1/configure --enable-optimizations
$ make -j $(nproc)
$ sudo -H make altinstall
$ cd ../

2. Build cmake 3.13.5

$ sudo apt-get install -y protobuf-compiler libprotobuf-dev openssl libssl-dev libcurl4-openssl-dev
$ wget https://github.com/Kitware/CMake/releases/download/v3.13.5/cmake-3.13.5.tar.gz
$ tar xvf cmake-3.13.5.tar.gz
$ rm cmake-3.13.5.tar.gz
$ cd cmake-3.13.5/
$ ./bootstrap --system-curl
$ make -j$(nproc)
$ echo 'export PATH='${PWD}'/bin/:$PATH' >> ~/.bashrc
$ source ~/.bashrc
$ cd ../

3. Prepare header

$ mkdir python3.9
$ mkdir python3.9/include
$ wget http://ftp.us.debian.org/debian/pool/main/p/python3.9/libpython3.9-dev_3.9.9-2_arm64.deb
$ ar x libpython3.9-dev_3.9.9-2_arm64.deb
$ tar -xvf data.tar.xz
$ cp ./usr/include/aarch64-linux-gnu/python3.9/pyconfig.h python3.9/include/
$ cp -r Python-3.9.1/Include/* python3.9/include/

4. Build TensorRT pybinding

$ git clone https://github.com/pybind/pybind11.git
$ git clone -b release/8.0 https://github.com/NVIDIA/TensorRT.git
$ cd TensorRT
$ git submodule update --init --recursive
$ cd python/
$ TRT_OSSPATH=${PWD}/.. EXT_PATH=${PWD}/../.. TARGET=aarch64 PYTHON_MINOR_VERSION=9 ./build.sh
$ python3.9 -m pip install build/dist/tensorrt-8.0.1.6-cp39-none-linux_aarch64.whl


Caffe

Below are the steps to build the Caffe library.

Verified environment:

  • JetPack4.6 + Xavier
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/install_caffe_jp46.sh -O install_caffe_jp46.sh
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/0001-patch-for-jp4.6.patch -O 0001-patch-for-jp4.6.patch
$ ./install_caffe_jp46.sh
$ source ~/.bashrc


MXNet

Below are the steps to build the MXNet 1.8.0 library.

Verified environment:

  • JetPack4.5.1 + Xavier
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/mxnet_v1.8.x.patch -O mxnet_v1.8.x.patch
$ wget https://raw.githubusercontent.com/AastaNV/JEP/master/elinux/autobuild_mxnet.sh -O autobuild_mxnet.sh
$ sudo chmod +x autobuild_mxnet.sh
$ ./autobuild_mxnet.sh Xavier
$ cd mxnet/build/
$ pip3 install mxnet-1.8.0-py3-none-any.whl


Common Error

"Unsupported ONNX data type: UINT8 (2)"

This error is from TensorRT. The root cause is that ONNX expects the input image to be INT8 but TensorRT uses Float32.

To solve this issue, you can modify the input data format of ONNX with our graphsurgeon API.

$ sudo apt-get install python3-pip libprotobuf-dev protobuf-compiler
$ git clone https://github.com/NVIDIA/TensorRT.git
$ cd TensorRT/tools/onnx-graphsurgeon/
$ make install
import onnx_graphsurgeon as gs
import onnx
import numpy as np

graph = gs.import_onnx(onnx.load("model.onnx"))
for inp in graph.inputs:
    inp.dtype = np.float32

onnx.save(gs.export_onnx(graph), "updated_model.onnx")


"Illegal instruction (core dumped)"

This is a known issue in NumPy v1.19.5.

To solve this issue, you can either downgrade your NumPy into 1.19.4 or manually update an environment variable.

  • Downgrade NumPy
$ sudo apt-get install python3-pip
$ pip3 install Cython
$ pip3 install numpy==1.19.4
  • Update environment variable
$ export OPENBLAS_CORETYPE=ARMV8