tensorflow模型安装与测试

一 tensorflow安装（安装过的跳过）
pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple/ tensorflow==2.0.0b1

二 下载所需文件

	elephant-299.jpg 
	classify_image_graph_def-with_shapes.pb	imagenet_2012_challenge_label_map_proto.pbtxt 
	imagenet_synset_to_human_label_map.txt 
（下载网站：
https://github.com/dmlc/web-data/raw/main/tensorflow/models/InceptionV1/）

文件保存路径：elephant-299.jpg、 imagenet_2012_challenge_label_map_proto.pbtxt 、imagenet_synset_to_human_label_map.txt 保存在/home5/yunji.he/.tvm_test_data/data目录下。classify_image_graph_def-with_shapes.pb文件保存在/home5/yunji.he/.tvm_test_data/tf/InceptionV1

三 测试
（1）导入头文件

import tvm
from tvm import te
from tvm import relay

# os and numpy
import numpy as np
import os.path

# Tensorflow imports
import tensorflow as tf

try:
    tf_compat_v1 = tf.compat.v1
except ImportError:
    tf_compat_v1 = tf

# Tensorflow utility functions
import tvm.relay.testing.tf as tf_testing

# Base location for model related files.
repo_base = "https://github.com/dmlc/web-data/raw/main/tensorflow/models/InceptionV1/"

# Test image
img_name = "elephant-299.jpg"
image_url = os.path.join(repo_base, img_name)
（2）
model_name = "classify_image_graph_def-with_shapes.pb"
model_url = os.path.join(repo_base, model_name)

# Image label map
map_proto = "imagenet_2012_challe