学习进度笔记14

观看Tensorflow案例实战视频课程14 加载训练好的VGG网络模型

def net(data_path,input_image):
    layers=(
        'conv1_1','relu1_1','conv1_2','relu1_2','pool1',
        'conv2_1','relu2_1','conv2_2','relu2_2','pool2',
        'conv3_1','relu3_1','conv3_2','relu3_2','conv3_3',
        'relu3_3','conv3_4','relu3_4','pool3',
        'conv4_1','relu4_1','conv4_2','relu4_2','conv4_3',
        'relu4_3','conv4_4','relu4_4','pool4',
        'conv5_1','relu5_1','conv5_2','relu5_2','conv5_3',
        'relu5_3','conv5_4','relu5_4','pool5',
    )
    data=scipy.io.loadmat(data_path)
    mean=data['normalization'][0][0][0]
    mean_pixel=np.mean(mean,axis=(0,1))
    weights=data['layers'][0]
    net={}

cwd=os.getcwd()
VGG_PATH=cwd+"/data/imagenet-vgg-verydeep-19.mat"
data=scipy.io.loadmat(VGG_PATH)
#print(data.keys())
mean=data['normalization'][0][0][0]
mean_pixel=np.mean(mean,axis=(0,1))
print(mean_pixel)
weights=data['layers'][0]
#print(weights)
#print(weights[0][0][0][0][0].shape)
#conv_1 w
print(weights[0][0][0][0][0][0].shape)
#conv_1 b
print(weights[0][0][0][0][0][1].shape)