首页 > 学术百科

Keras：使用InceptionV3、ResNet50模型进行图片分类

Keras：使⽤InceptionV3、ResNet50模型进⾏图⽚分类

渗透压力

⽤Keras构建⽹络并使⽤其提供的预训练权重进⾏简单的图像分类．

其中decode_predictions()将结果解码为元组列表，内容包括（类别，描述，概率）．

养老地产运营模式

使⽤Inc eptio nV3进⾏图⽚分类

幻想曲古筝#!/usr/bin/python

# coding:utf8

from keras.applications.inception_v3 import InceptionV3

from keras.applications.inception_v3 import decode_predictions

from keras.preprocessing import image

import numpy as np

import cv2

model = InceptionV3(weights='imagenet', include_top=True)

img_path = "bird1.jpg"用友华表cell插件

img = image.load_img(img_path, target_size=(299, 299))

img = image.img_to_array(img) / 255.0

img = np.expand_dims(img, axis=0) # 为batch添加第四维

predictions = model.predict(img)

print('Predicted:', decode_predictions(predictions, top=3))

description = decode_predictions(predictions, top=3)[0][0][1]

src = cv2.imread(img_path)

cv2.putText(src, description, (50,50), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255,0,0), 2)

cv2.imshow("Predicted", src)

cv2.waitKey()

输出：

('Predicted:', [[(u'n02110185', u'Siberian_husky', 0.734093), (u'n02109961', u'Eskimo_dog', 0.17709365), (u'n02110063', u'malamute', 0.013321317

使⽤R esN et50进⾏图⽚分类

#!/usr/bin/python

# coding:utf8

from snet50 import ResNet50

from keras.preprocessing import image

from snet50 import preprocess_input, decode_predictions

import numpy as np

import cv2

model = ResNet50(weights='imagenet')

img_path = 'bird.jpg'

img = image.load_img(img_path, target_size=(224, 224))

img = image.img_to_array(img)

img = np.expand_dims(img, axis=0)

img = preprocess_input(img)

predictions = model.predict(img)

print('Predicted:', decode_predictions(predictions, top=3))

description = decode_predictions(predictions, top=3)[0][0][1]

src = cv2.imread(img_path)

cv2.putText(src, description, (50,50), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255,0,0), 2)

cv2.imshow("Predicted", src)

cv2.waitKey()金钱的魔力教学设计

纪录片面条之路输出：

('Predicted:', [[(u'n01531178', u'goldfinch', 0.88929653), (u'n01537544', u'indigo_bunting', 0.0318476), (u'n01560419', u'bulbul', 0.024045745)]])

本文发布于:2024-09-21 22:40:35，感谢您对本站的认可！

本文链接：https://www.17tex.com/xueshu/453341.html

上一篇：DesignCompiler（七）——环境、设计规则和面积约束

下一篇：语音识别中的WFST和语言模型

标签：博主包括列表

留言与评论（共有 0 条评论）