def get_data_info():
"""
加载上周课程中的图片数据集
:return: 数据集字典
"""
data_info_dict = dict()
train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes = load_dataset(
)
print '训练集维度： %s' % str(train_set_x_orig.shape)
print '测试集维度： %s' % str(test_set_x_orig.shape)
# 原始数据
data_info_dict['train_set_x_orig'] = train_set_x_orig
data_info_dict['train_set_y_orig'] = train_set_y_orig
data_info_dict['test_set_x_orig'] = test_set_x_orig
data_info_dict['test_set_y_orig'] = test_set_y_orig
# 一维化数据
data_info_dict['train_set_x'] = train_set_x_orig.reshape(
train_set_x_orig.shape[0], -1).T / 255.0
data_info_dict['test_set_x'] = test_set_x_orig.reshape(
test_set_x_orig.shape[0], -1).T / 255.0
# 信息
data_info_dict['classes'] = classes
data_info_dict['n_train'] = train_set_x_orig.shape[0]
data_info_dict['n_test'] = test_set_x_orig.shape[0]
data_info_dict['pic_size'] = (train_set_x_orig[1:])
return data_info_dict
p = np.zeros((1, m))
# 根据参数前向传播
probas, caches = L_model_forward(X, parameters)
for i in range(0, probas.shape[1]):
if probas[0, i] > 0.5:
p[0, i] = 1
else:
p[0, i] = 0
print("准确度为: " + str(float(np.sum((p == y)) / m)))
return p
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = lr_utils.load_dataset(
)
train_x_flatten = train_set_x_orig.reshape(train_set_x_orig.shape[0], -1).T
test_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T
train_x = train_x_flatten / 255
train_y = train_set_y
test_x = test_x_flatten / 255
test_y = test_set_y
layers_dims = [12288, 20, 7, 5, 1] # 5-layer model
parameters = mlp(train_x,
train_y,
layers_dims,
learning_rate=0.0075,
num_iterations=2500,
for i in range(0, probas.shape[1]):
if probas[0, i] > 0.5:
p[0, i] = 1
else:
p[0, i] = 0
#print results
#print ("predictions: " + str(p))
#print ("true labels: " + str(y))
print("Accuracy: " + str(np.sum((p == y) / m)))
return p
if __name__ == "__main__":
np.random.seed(1)
train_x_orig, train_y, test_x_orig, test_y, classes = load_dataset()
train_x = train_x_orig.reshape(train_x_orig.shape[0], -1).T / 255.
test_x = test_x_orig.reshape(test_x_orig.shape[0], -1).T / 255.
# index = 10
# plt.imshow(train_x_orig[index])
# plt.show()
m_train = train_x_orig.shape[0]
m_test = test_x_orig.shape[0]
num_px = train_x_orig.shape[1]
n_h = 7
n_y = 1
layer_dims = (num_px * num_px * 3, 5, 7, 2, 1)
# layer_dims = (num_px*num_px*3,n_h,n_y)
# params = two_layer_model(train_x,train_y,layer_dims=layer_dims,learning_rate=0.05,num_iter=2500,print_cost=True)
# pred_train = predict(train_x,train_y,params)