Caffe2(3)----下載現成的模型並使用

Caffe2訓練好的模型可在Model Zoo下載，下載的命令很簡單，接下來以下載和使用squeezenet為例，進行簡單說明。

 

1.瀏覽可下載的模型

已有模型都放在github上，地址：https://github.com/caffe2/caffe2/wiki/Model-Zoo，當前有caffe和caffe2兩種版本的選擇。

 

2.選擇下載模型

注意名字為小寫，有些會加下划線，我們這里選擇caffe2的版本

下載並安裝（安裝目錄為/usr/local/caffe2/python/models），命令如下：

python -m caffe2.python.models.download --install squeezenet

有時候需要sudo的權限，則要改為執行如下命令：

sudo PYTHONPATH=/usr/local python -m caffe2.python.models.download --install squeezenet

 

3.應用模型

我們嘗試從網上下載一些代碼，然后進行預測，在官方代碼的基礎上做了一些改動，代碼如下：

# load up the caffe2 workspace
from caffe2.python import workspace
# choose your model here (use the downloader first)
from caffe2.python.models import squeezenet as mynet
# helper image processing functions
import caffe2.python.tutorials.helpers as helpers

import skimage.io 
from matplotlib import pyplot as plt

# load the pre-trained model
init_net = mynet.init_net
predict_net = mynet.predict_net
# you must name it something
predict_net.name = "squeezenet_predict"
workspace.RunNetOnce(init_net)
workspace.CreateNet(predict_net)
p = workspace.Predictor(init_net.SerializeToString(), predict_net.SerializeToString())

# use whatever image you want (local files or urls)
#img_pth = "https://upload.wikimedia.org/wikipedia/commons/thumb/7/7b/Orange-Whole-%26-Split.jpg/1200px-Orange-Whole-%26-Split.jpg"
#img_pth = "https://upload.wikimedia.org/wikipedia/commons/a/ac/Pretzel.jpg"
img_pth = "https://cdn.pixabay.com/photo/2015/02/10/21/28/flower-631765_1280.jpg"
# average mean to subtract from the image
mean = 128
# the size of images that the model was trained with
input_size = 227

# use the image helper to load the image and convert it to NCHW
img = helpers.loadToNCHW(img_pth, mean, input_size)

# submit the image to net and get a tensor of results

results = p.run([img])
response = helpers.parseResults(results)
# and lookup our result from the list
print response

#show result on image
img_mat = skimage.io.imread(img_pth)
skimage.io.imshow(img_mat)
plt.title(response,{'fontsize': '20'})
plt.savefig('pretzel.jpg')
plt.show()

注意別忘記把推理的文件inference_codes.txt放在程序的當前目錄

 

4.結果

對三張圖片分類的結果及其概率如圖所示

5.參考資料

[1].Model Zoo Doc

[2].Model Zoo Github

[3].賈揚清等人撰文詳解Caffe2：從強大新能力到上手教程