图像分类

使用 Keras 进行图像建模

Ariel Rokem

Senior Data Scientist, University of Washington

图像分类

图像分类：训练

图像分类：评估

类别数据表示：独热编码

labels = ["shoe", "dress", "shoe", "t-shirt", 
          "shoe", "t-shirt", "shoe", "dress"]

类别数据表示：独热编码

array([[0., 0., 1.],    <= shoe
       [0., 1., 0.],    <= dress
       [0., 0., 1.],    <= shoe
       [1., 0., 0.],    <= t-shirt
       [0., 0., 1.],    <= shoe
       [1., 0., 0.],    <= t-shirt
       [0., 0., 1.],    <= shoe
       [0., 1., 0.]])   <= dress

独热编码

categories = np.array(["t-shirt", "dress", "shoe"])

n_categories = 3
ohe_labels = np.zeros((len(labels), n_categories))

for ii in range(len(labels)):

    jj = np.where(categories == labels[ii])

    ohe_labels[ii, jj] = 1

独热编码：测试预测

test

array([[0., 0., 1.], 
       [0., 1., 0.], 
       [0., 0., 1.], 
       [0., 1., 0.], 
       [0., 0., 1.],
       [0., 0., 1.],
       [0., 0., 1.],
       [0., 1., 0.]])

(test * prediction).sum()

6.0

prediction

array([[0., 0., 1.], 
       [0., 1., 0.], 
       [0., 0., 1.], 
       [1., 0., 0.], <= 错误
       [0., 0., 1.],
       [1., 0., 0.], <= 错误
       [0., 0., 1.], 
       [0., 1., 0.]])

Passons à la pratique !

使用 Keras 进行图像建模