def test10RandomImgs():
# 读取测试集结果
dl = DataLoader('MNIST', './datasets/MNIST/')
test_images, test_labels = dl.Load('test')
# 生成10个连续的随机数
idx = np.random.randint(0, test_images.shape[0] - 10)
random_image = test_images[idx:idx + 10, :]
# testlabel = nn.test(random_image.T)
MNIST_test = NN()
MNIST_test.loadParams()
out = MNIST_test.forward(random_image.T - 33.318421, 'test')
exp_out = np.exp(out)
softmax_out = exp_out / np.sum(exp_out, axis=0)
# 找到最大值索引，作为分类结果
cls_res = np.argmax(softmax_out, axis=0)
# 显示图像
for i in range(0, 10):
plt.subplot(2, 5, i + 1)
plt.title('分类: %d' % cls_res[i])
# 关闭坐标刻度
plt.xticks([])
plt.yticks([])
plt.imshow(np.reshape(random_image[i], [28, 28]), cmap='gray')
plt.show()
model_path = './model/mnist_mlp_epoch9.model'
# Construct nn
MLP = NN()
MLP.add(SimpleBatchNorm(name="data_batchnorm", istraining=False))
MLP.add(Fullyconnected(784, 512, name="fc1"))
MLP.add(Relu(name="fc1_relu"))
MLP.add(SimpleBatchNorm(name='fc1_batchnorm'))
MLP.add(Fullyconnected(512, 512, name="fc2"))
MLP.add(Relu(name="fc2_relu"))
MLP.add(Fullyconnected(512, 10, name="fc3"))
# Load model
MLP.load_model(model_path)
for parent, dirnames, filenames in os.walk(img_dir):
for filename in filenames:
if filename.endswith("jpg") or filename.endswith("png"):
img_path = os.path.join(parent, filename)
pil_img = Image.open(img_path).convert('L')
pil_img = pil_img.resize((28, 28), Image.ANTIALIAS)
img = np.array(pil_img)
out_data = MLP.forward(img.reshape((1, 784)))
# Softmax
probs = np.exp(out_data -
out_data.max(axis=1).reshape((out_data.shape[0],
1)))
probs /= probs.sum(axis=1).reshape((out_data.shape[0], 1))
print img_path, 'predict:', np.argmax(probs)
MLP.add(Fullyconnected(512, 512, name="fc2"))
MLP.add(Relu(name="fc2_relu"))
MLP.add(Fullyconnected(512, 10, name="fc3"))
# Load model
MLP.load_model(model_path)
# Load mnist data
mnist = mnist(path="./data/", batch_size=1, test=True)
num_imgs = mnist.get_num()
pos = 0
total_time = 0
for i in range(num_imgs):
img, label = mnist.get_batch()
t1 = time.time()
out_data = MLP.forward(img)
t2 = time.time()
# Softmax
probs = np.exp(out_data -
out_data.max(axis=1).reshape((out_data.shape[0], 1)))
probs /= probs.sum(axis=1).reshape((out_data.shape[0], 1))
pos += np.sum(label == probs.argmax(axis=1))
print "test img%d, time:%.5f" % (i, t2 - t1)
total_time += t2 - t1
print "acc:", pos / float(num_imgs)
print "average time:", total_time / float(num_imgs)