Host JetsonNano
  HostName 192.168.1.6
  User bbuf

Linux bbuf-desktop 4.9.201-tegra #1 SMP PREEMPT Fri Feb 19 08:40:32 PST 2021 aarch64 aarch64 aarch64 GNU/Linux

sudo cp /etc/apt/sources.list /etc/apt/sources_init.list

sudo gedit /etc/apt/sources.list

deb http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic main multiverse restricted universe
deb http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-security main multiverse restricted universe
deb http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-updates main multiverse restricted universe
deb http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-backports main multiverse restricted universe
deb-src http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic main multiverse restricted universe
deb-src http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-security main multiverse restricted universe
deb-src http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-updates main multiverse restricted universe
deb-src http://mirrors.tuna.tsinghua.edu.cn/ubuntu-ports/ bionic-backports main multiverse restricted universe

git clone --recursive https://github.com/apache/tvm tvm
cd tvm
mkdir build
cp cmake/config.cmake build
cd build
cmake ..
make -j4
export TVM_HOME=/path/to/tvm
export PYTHONPATH=$TVM_HOME/python:${PYTHONPATH}

CMake Error at cmake/utils/FindLLVM.cmake:47 (find_package):
  Could not find a package configuration file provided by "LLVM" with any of
  the following names:

    LLVMConfig.cmake
    llvm-config.cmake

git clone https://github.com/llvm/llvm-project llvm-project
cd llvm-project
mkdir build
cd build
cmake -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_PROJECTS=lld -DCMAKE_INSTALL_PREFIX=/usr/local ../../llvm-project/llvm
make -j4 && sudo make install

wget https://github.com/Kitware/CMake/releases/download/v3.14.4/cmake-3.14.4.tar.gz
tar xvf cmake-3.14.4.tar.gz
cd cmake-3.14.4
./bootstrap --prefix=/usr
make
sudo make install

export TVM_HOME=/home/bbuf/tvm_project/tvm
export PYTHONPATH=$TVM_HOME/python:${PYTHONPATH}

sudo apt-get update
sudo apt-get install -y git build-essential libopenblas-dev libopencv-dev python3-pip
sudo pip3 install -U pip

wget https://mxnet-public.s3.us-east-2.amazonaws.com/install/jetson/1.6.0/mxnet_cu102-1.6.0-py2.py3-none-linux_aarch64.whl
sudo pip3 install mxnet_cu102-1.6.0-py2.py3-none-linux_aarch64.whl

import tvm
from tvm import te
import tvm.relay as relay
from tvm import rpc
from tvm.contrib import utils, graph_executor as runtime
from tvm.contrib.download import download_testdata

from mxnet.gluon.model_zoo.vision import get_model
from PIL import Image
import numpy as np

# one line to get the model
block = get_model("resnet18_v1", pretrained=True)

img_url = "https://github.com/dmlc/mxnet.js/blob/main/data/cat.png?raw=true"
img_name = "cat.png"
img_path = download_testdata(img_url, img_name, module="data")
image = Image.open(img_path).resize((224, 224))


def transform_image(image):
    image = np.array(image) - np.array([123.0, 117.0, 104.0])
    image /= np.array([58.395, 57.12, 57.375])
    image = image.transpose((2, 0, 1))
    image = image[np.newaxis, :]
    return image


x = transform_image(image)

synset_url = "".join(
    [
        "https://gist.githubusercontent.com/zhreshold/",
        "4d0b62f3d01426887599d4f7ede23ee5/raw/",
        "596b27d23537e5a1b5751d2b0481ef172f58b539/",
        "imagenet1000_clsid_to_human.txt",
    ]
)
synset_name = "imagenet1000_clsid_to_human.txt"
synset_path = download_testdata(synset_url, synset_name, module="data")
with open(synset_path) as f:
    synset = eval(f.read())

# We support MXNet static graph(symbol) and HybridBlock in mxnet.gluon
shape_dict = {"data": x.shape}
mod, params = relay.frontend.from_mxnet(block, shape_dict)
# we want a probability so add a softmax operator
func = mod["main"]
func = relay.Function(func.params, relay.nn.softmax(func.body), None, func.type_params, func.attrs)

batch_size = 1
num_classes = 1000
image_shape = (3, 224, 224)
data_shape = (batch_size,) + image_shape

local_demo = True

if local_demo:
    target = tvm.target.Target("llvm")
else:
    target = tvm.target.Target("llvm")

with tvm.transform.PassContext(opt_level=3):
    lib = relay.build(func, target, params=params)

# After `relay.build`, you will get three return values: graph,
# library and the new parameter, since we do some optimization that will
# change the parameters but keep the result of model as the same.

# Save the library at local temporary directory.
tmp = utils.tempdir()
lib_fname = tmp.relpath("net.tar")
lib.export_library(lib_fname)

local_demo = True

if local_demo:
    target = tvm.target.Target("llvm")
    # target = tvm.target.Target("nvidia/jetson-nano")
    # target_host = "llvm"
    # assert target.kind.name == "cuda"
    # assert target.attrs["arch"] == "sm_53"
    # assert target.attrs["shared_memory_per_block"] == 49152
    # assert target.attrs["max_threads_per_block"] == 1024
    # assert target.attrs["thread_warp_size"] == 32
    # assert target.attrs["registers_per_block"] == 32768
else:
    target = tvm.target.Target("llvm")

with tvm.transform.PassContext(opt_level=7):
    lib = relay.build(func, target, target_host=target_host, params=params)

tmp = utils.tempdir()
lib_fname = tmp.relpath("net.tar")
lib.export_library(lib_fname)


# create the remote runtime module
dev = tvm.cuda(0)
module = runtime.GraphModule(lib["default"](dev))
time_start = time.time()
# set input data
module.set_input("data", tvm.nd.array(x.astype("float32")))
# run
module.run()

time_end = time.time()

print('time cost', time_end-time_start,'s')
# get output
out = module.get_output(0)
# get top1 result
top1 = np.argmax(out.numpy())
print("TVM prediction top-1: {}".format(synset[top1]))

TVM prediction top-1: tiger cat

time cost 0.16585731506347656 s

WARNING:root:Failed to download tophub package for cuda: <urlopen error [Errno 111] Connection refused>

git clone https://github.com/tlc-pack/tophub
cp tophub/tophub/ /home/bbuf/.tvm -rf

Extract tasks...
Compile...
Evaluate inference time cost...
Mean inference time (std dev): 154.54 ms (0.47 ms)