1、編譯需要打開的選項：

創(chuàng)新互聯(lián)建站是一家集網(wǎng)站建設(shè),觀山湖企業(yè)網(wǎng)站建設(shè),觀山湖品牌網(wǎng)站建設(shè),網(wǎng)站定制,觀山湖網(wǎng)站建設(shè)報價,網(wǎng)絡(luò)營銷,網(wǎng)絡(luò)優(yōu)化,觀山湖網(wǎng)站推廣為一體的創(chuàng)新建站企業(yè)，幫助傳統(tǒng)企業(yè)提升企業(yè)形象加強企業(yè)競爭力?？沙浞譂M足這一群體相比中小企業(yè)更為豐富、高端、多元的互聯(lián)網(wǎng)需求。同時我們時刻保持專業(yè)、時尚、前沿，時刻以成就客戶成長自我，堅持不斷學(xué)習、思考、沉淀、凈化自己，讓我們?yōu)楦嗟钠髽I(yè)打造出實用型網(wǎng)站。

set(USE_SORT ON)

參考資料：

discuss.tvm.ai/t/solved-cant-run-tutorials-ssd-model-on-my-own-cpu/2005

2、編譯gpu模型：

編譯時，打開編譯cuda選項：tvm_option(USE_CUDA "Build with CUDA" ON)

在jetson nano上編譯GPU版本時，需要將cuda加入到環(huán)境變量里面去：

export CUBA_HOME=/usr/local/cuda-10.0:$PATH

export LD_LIBRARY_PATH=/usr/local/cuda-10.0/lib64:$LD_LIBRARY_PATH

export PATH=/usr/local/cuda-10.0/bin:$PATH

將target = tvm.target.create("llvm -mcpu=haswell")替換為：target = "cuda"

參考資料：

github.com/

3、Andorid編譯

cp make/config.mk

APP_ABI = armeabi-v7a

./make_standalone_toolchain.py –arch arm --api 23 --install-dir /opt/android-toolchain-armv7 -mfloat-abi=soft

參考資料：

discuss.tvm.ai

4、LLVM 在windows上編譯

1)下載LLVM源碼

首先下載LLVM源碼，下載地址為：

github.com/MirrorYuChen/llvm-project/tree/release/6.x

這里對應(yīng)LLVM版本為6.x，后面需要用LLD工具，這個源碼里面就自帶有，然后在LLVM文件夾下面新建一個build文件夾，并在此文件夾路徑下打開cmd窗口，輸入如下命令：

cmake -G "Visual Studio 15 2017 Win64" .. -Thost=x64 -DLLVM_ENABLE_PROJECTS=lld

打開生成的llvm.sln項目，切換到release x64模式編譯，大約需要1小時時間編譯完成，并運行install。

Jetson nano:

>> 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 -j3 && make install

2)下載tvm源碼

git clone --recursive https://github.com/dmlc/tvm/

在tvm項目路徑下新建build子文件夾，并在當前路徑下新建一個bash.sh文件，文件內(nèi)容為：

cmake -G "Visual Studio 15 2017 Win64" -DCMAKE_BUILD_TYPE=Release \

-DCMAKE_CONFIGURATION_TYPES="Release" .. \

-DLLVM_DIR=D:\softW\LLVM\lib\cmake\llvm

后面LLVM路徑對應(yīng)到剛install生成的LLVM路徑，打開生成的tvm.sln項目，編譯運行。

3)安裝

先新建一個conda環(huán)境變量：

conda create -n tf python==3.5

激活環(huán)境：

activate tf

分別安裝tensorflow和mxnet

pip install tensorflow

pip install mxnet

分別進入tvm、topi、nnvm文件夾下，運行下面命令進行安裝

python setup.py install

安裝完成之后，可以進入tvm的tutorials子文件夾下，運行相關(guān)例程。

這里是一個ssd運行例程：

測試代碼為：

#!/usr/bin/python3

import os

import tvm

import numpy as np

import time

from tvm.contrib.download import download

from tvm.contrib import graph_runtime

current_milli_time = lambda: int(round(time.time() * 1000))

test_image = "dog.jpg"

dshape = (1, 3, 512, 512)

#dshape = (1, 3, 608, 608)

dtype = "float32"

image_url = "/upload/otherpic49/113691.jpg"

download(image_url, test_image)

# Preprocess image

import cv2

test_image_path = test_image

image = cv2.imread(test_image_path)

img_data = cv2.resize(image, (dshape[2], dshape[3]))

img_data = img_data[:, :, (2, 1, 0)].astype(np.float32)

img_data -= np.array([123, 117, 104])

img_data = np.transpose(np.array(img_data), (2, 0, 1))

ctx = tvm.cpu()

target="llvm"

#base = "deploy_ssd_resnet50_512/{}/".format(target)

#base = "deploy_ssd_inceptionv3_512/{}/".format(target)

#base = "deploy_ssd_mobilenet_512/{}/".format(target)

#base = "deploy_ssd_mobilenet_608/{}/".format(target)

#base = "cpu-model/"

base = "./"

path_lib = base + "model.so"

path_graph = base + "model.json"

path_param = base + "model.params"

graph = open(path_graph).read()

params = bytearray(open(path_param, "rb").read())

lib = tvm.module.load(path_lib)

class_names = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair",

"cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant",

"sheep", "sofa", "train", "tvmonitor"]

######################################################################

# Create TVM runtime and do inference

# Build TVM runtime

m = graph_runtime.create(graph, lib, ctx)

m.load_params(params)

input_data = tvm.nd.array(img_data.astype(dtype))

# dryrun

m.run(data = input_data)

# execute

t1 = current_milli_time()

m.run(data = input_data)

# get outputs

tvm_output = m.get_output(0)

t2 = current_milli_time()

print(base)

print("time: {} ms".format(t2 - t1))

out = tvm_output.asnumpy()[0]

i = 0無錫×××醫(yī)院 https://yyk.familydoctor.com.cn/20612/

for det in out:

cid = int(det[0])

if cid < 0:

continue

score = det[1]

if score < 0.5:

continue

i += 1

print(i, class_names[cid], det)

######################################################################

# Display result

def display(img, out, thresh=0.5):

import random

import matplotlib as mpl

import matplotlib.pyplot as plt

mpl.rcParams['figure.figsize'] = (10, 10)

pens = dict()

plt.clf()

plt.imshow(img)

for det in out:

cid = int(det[0])

if cid < 0:

continue

score = det[1]

if score < thresh:

continue

if cid not in pens:

pens[cid] = (random.random(), random.random(), random.random())

scales = [img.shape[1], img.shape[0]] * 2

xmin, ymin, xmax, ymax = [int(p * s) for p, s in zip(det[2:6].tolist(), scales)]

rect = plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False,

edgecolor=pens[cid], linewidth=3)

plt.gca().add_patch(rect)

text = class_names[cid]

plt.gca().text(xmin, ymin-2, '{:s} {:.3f}'.format(text, score),

bbox=dict(facecolor=pens[cid], alpha=0.5),

fontsize=12, color='white')

plt.show()

image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

display(image, tvm_output.asnumpy()[0], thresh=0.45)

代碼來自于github