def build_model(self): # 建立网络结构
# TODO：建立三层神经网络结构
print('Building multi-layer perception model...')
self.fc1 = FullyConnectedLayer(self.input_size, self.hidden1)
self.relu1 = ReLULayer()
self.fc2 = FullyConnectedLayer(self.hidden1, self.hidden2)
self.relu2 = ReLULayer()
self.fc3 = FullyConnectedLayer(self.hidden2, self.out_classes)
self.softmax = SoftmaxLossLayer()
self.update_layer_list = [self.fc1, self.fc2, self.fc3]
def build_model(self):
# TODO：定义VGG19 的网络结构
print('Building vgg-19 model...')
self.layers = {}
self.layers['conv1_1'] = ConvolutionalLayer(3, 3, 64, 1, 1)
self.layers['relu1_1'] = ReLULayer()
self.layers['conv1_2'] = ConvolutionalLayer(3, 64, 64, 1, 1)
self.layers['relu1_2'] = ReLULayer()
self.layers['pool1'] = MaxPoolingLayer(2, 2)
self.layers['conv2_1'] = ConvolutionalLayer(3, 64, 128, 1, 1)
self.layers['relu2_1'] = ReLULayer()
self.layers['conv2_2'] = ConvolutionalLayer(3, 128, 128, 1, 1)
self.layers['relu2_2'] = ReLULayer()
self.layers['pool2'] = MaxPoolingLayer(2, 2)
self.layers['conv3_1'] = ConvolutionalLayer(3, 128, 256, 1, 1)
self.layers['relu3_1'] = ReLULayer()
self.layers['conv3_2'] = ConvolutionalLayer(3, 256, 256, 1, 1)
self.layers['relu3_2'] = ReLULayer()
self.layers['conv3_3'] = ConvolutionalLayer(3, 256, 256, 1, 1)
self.layers['relu3_3'] = ReLULayer()
self.layers['conv3_4'] = ConvolutionalLayer(3, 256, 256, 1, 1)
self.layers['relu3_4'] = ReLULayer()
self.layers['pool3'] = MaxPoolingLayer(2, 2)
self.layers['conv4_1'] = ConvolutionalLayer(3, 256, 512, 1, 1)
self.layers['relu4_1'] = ReLULayer()
self.layers['conv4_2'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu4_2'] = ReLULayer()
self.layers['conv4_3'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu4_3'] = ReLULayer()
self.layers['conv4_4'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu4_4'] = ReLULayer()
self.layers['pool4'] = MaxPoolingLayer(2, 2)
self.layers['conv5_1'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_1'] = ReLULayer()
self.layers['conv5_2'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_2'] = ReLULayer()
self.layers['conv5_3'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_3'] = ReLULayer()
self.layers['conv5_4'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_4'] = ReLULayer()
self.layers['pool5'] = MaxPoolingLayer(2, 2)
self.layers['flatten'] = FlattenLayer([512, 7, 7], [512 * 7 * 7])
self.layers['fc6'] = FullyConnectedLayer(512 * 7 * 7, 4096)
self.layers['relu6'] = ReLULayer()
self.layers['fc7'] = FullyConnectedLayer(4096, 4096)
self.layers['relu7'] = ReLULayer()
self.layers['fc8'] = FullyConnectedLayer(4096, 1000)
self.layers['softmax'] = SoftmaxLossLayer()
self.update_layer_list = []
for layer_name in self.layers.keys():
if 'conv' in layer_name or 'fc' in layer_name:
self.update_layer_list.append(layer_name)
def build_model(self):
# TODO：定义VGG19 的网络结构
print('Building vgg-19 model...')
self.layers = {}
# ConvolutionalLayer: kernel_size, channel_in, channel_out, padding, stride
# MaxPoolingLayer: kernel_size, stride
# FlattenLayer: input_shape, output_shape
self.layers['conv1_1'] = ConvolutionalLayer(3, 3, 64, 1, 1)
self.layers['relu1_1'] = ReLULayer()
self.layers['conv1_2'] = ConvolutionalLayer(3, 64, 64, 1, 1)
self.layers['relu1_2'] = ReLULayer()
self.layers['pool1'] = MaxPoolingLayer(2, 2)
self.layers['conv2_1'] = ConvolutionalLayer(3, 64, 128, 1, 1)
self.layers['relu2_1'] = ReLULayer()
self.layers['conv2_2'] = ConvolutionalLayer(3, 128, 128, 1, 1)
self.layers['relu2_2'] = ReLULayer()
self.layers['pool2'] = MaxPoolingLayer(2, 2)
self.layers['conv3_1'] = ConvolutionalLayer(3, 128, 256, 1, 1)
self.layers['relu3_1'] = ReLULayer()
self.layers['conv3_2'] = ConvolutionalLayer(3, 256, 256, 1, 1)
self.layers['relu3_2'] = ReLULayer()
self.layers['conv3_3'] = ConvolutionalLayer(3, 256, 256, 1, 1)
self.layers['relu3_3'] = ReLULayer()
self.layers['conv3_4'] = ConvolutionalLayer(3, 256, 256, 1, 1)
self.layers['relu3_4'] = ReLULayer()
self.layers['pool3'] = MaxPoolingLayer(2, 2)
self.layers['conv4_1'] = ConvolutionalLayer(3, 256, 512, 1, 1)
self.layers['relu4_1'] = ReLULayer()
self.layers['conv4_2'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu4_2'] = ReLULayer()
self.layers['conv4_3'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu4_3'] = ReLULayer()
self.layers['conv4_4'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu4_4'] = ReLULayer()
self.layers['pool4'] = MaxPoolingLayer(2, 2)
self.layers['conv5_1'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_1'] = ReLULayer()
self.layers['conv5_2'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_2'] = ReLULayer()
self.layers['conv5_3'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_3'] = ReLULayer()
self.layers['conv5_4'] = ConvolutionalLayer(3, 512, 512, 1, 1)
self.layers['relu5_4'] = ReLULayer()
self.layers['pool5'] = MaxPoolingLayer(2, 2)
self.layers['flatten'] = FlattenLayer(input_shape=[512, 7, 7],
output_shape=[25088])
self.layers['fc6'] = FullyConnectedLayer(25088, 4096)
self.layers['relu6'] = ReLULayer()
self.layers['fc7'] = FullyConnectedLayer(4096, 4096)
self.layers['relu7'] = ReLULayer()
self.layers['fc8'] = FullyConnectedLayer(4096, 1000)
self.layers['softmax'] = SoftmaxLossLayer()
self.update_layer_list = []
for layer_name in self.layers.keys():
if 'conv' in layer_name or 'fc' in layer_name:
self.update_layer_list.append(layer_name)
class MNIST_MLP(object):
def __init__(self, batch_size=100, input_size=784, hidden1=32, hidden2=16, out_classes=10, lr=0.01, max_epoch=1, print_iter=100):
self.batch_size = batch_size
self.input_size = input_size
self.hidden1 = hidden1
self.hidden2 = hidden2
self.out_classes = out_classes
self.lr = lr
self.max_epoch = max_epoch
self.print_iter = print_iter
def load_mnist(self, file_dir, is_images = 'True'):
# Read binary data
bin_file = open(file_dir, 'rb')
bin_data = bin_file.read()
bin_file.close()
# Analysis file header
if is_images:
# Read images
fmt_header = '>iiii'
magic, num_images, num_rows, num_cols = struct.unpack_from(fmt_header, bin_data, 0)
else:
# Read labels
fmt_header = '>ii'
magic, num_images = struct.unpack_from(fmt_header, bin_data, 0)
num_rows, num_cols = 1, 1
data_size = num_images * num_rows * num_cols
mat_data = struct.unpack_from('>' + str(data_size) + 'B', bin_data, struct.calcsize(fmt_header))
mat_data = np.reshape(mat_data, [num_images, num_rows * num_cols])
print('Load images from %s, number: %d, data shape: %s' % (file_dir, num_images, str(mat_data.shape)))
return mat_data
def load_data(self):
# TODO: 调用函数 load_mnist 读取和预处理 MNIST 中训练数据和测试数据的图像和标记
print('Loading MNIST data from files...')
train_images = self.load_mnist(os.path.join(MNIST_DIR, TRAIN_DATA), True)
train_labels = self.load_mnist(os.path.join(MNIST_DIR, TRAIN_LABEL), False)
test_images = self.load_mnist(os.path.join(MNIST_DIR, TEST_DATA), True)
test_labels = self.load_mnist(os.path.join(MNIST_DIR, TEST_LABEL), False)
self.train_data = np.append(train_images, train_labels, axis=1)
self.test_data = np.append(test_images, test_labels, axis=1)
# self.test_data = np.concatenate((self.train_data, self.test_data), axis=0)
def shuffle_data(self):
print('Randomly shuffle MNIST data...')
np.random.shuffle(self.train_data)
def build_model(self): # 建立网络结构
# TODO：建立三层神经网络结构
print('Building multi-layer perception model...')
self.fc1 = FullyConnectedLayer(self.input_size, self.hidden1)
self.relu1 = ReLULayer()
self.fc2 = FullyConnectedLayer(self.hidden1, self.hidden2)
self.relu2 = ReLULayer()
self.fc3 = FullyConnectedLayer(self.hidden2, self.out_classes)
self.softmax = SoftmaxLossLayer()
self.update_layer_list = [self.fc1, self.fc2, self.fc3]
def init_model(self):
print('Initializing parameters of each layer in MLP...')
for layer in self.update_layer_list:
layer.init_param()
def load_model(self, param_dir):
print('Loading parameters from file ' + param_dir)
params = np.load(param_dir).item()
self.fc1.load_param(params['w1'], params['b1'])
self.fc2.load_param(params['w2'], params['b2'])
self.fc3.load_param(params['w3'], params['b3'])
def save_model(self, param_dir):
print('Saving parameters to file ' + param_dir)
params = {}
params['w1'], params['b1'] = self.fc1.save_param()
params['w2'], params['b2'] = self.fc2.save_param()
params['w3'], params['b3'] = self.fc3.save_param()
np.save(param_dir, params)
def forward(self, input): # 神经网络的前向传播
# TODO：神经网络的前向传播
h1 = self.fc1.forward(input)
h1 = self.relu1.forward(h1)
h2 = self.fc2.forward(h1)
h2 = self.relu2.forward(h2)
h3 = self.fc3.forward(h2)
prob = self.softmax.forward(h3)
return prob
def backward(self): # 神经网络的反向传播
# TODO：神经网络的反向传播
dloss = self.softmax.backward()
dh3 = self.fc3.backward(dloss)
dh2 = self.relu2.backward(dh3)
dh2 = self.fc2.backward(dh2)
dh1 = self.relu1.backward(dh2)
dh1 = self.fc1.backward(dh1)
def update(self, lr):
for layer in self.update_layer_list:
layer.update_param(lr)
def train(self):
max_batch = self.train_data.shape[0] / self.batch_size
print('Start training...')
for idx_epoch in range(self.max_epoch):
self.shuffle_data()
for idx_batch in range(max_batch):
batch_images = self.train_data[idx_batch*self.batch_size:(idx_batch+1)*self.batch_size, :-1]
batch_labels = self.train_data[idx_batch*self.batch_size:(idx_batch+1)*self.batch_size, -1]
prob = self.forward(batch_images)
loss = self.softmax.get_loss(batch_labels)
self.backward()
self.update(self.lr)
if idx_batch % self.print_iter == 0:
print('Epoch %d, iter %d, loss: %.6f' % (idx_epoch, idx_batch, loss))
def evaluate(self):
pred_results = np.zeros([self.test_data.shape[0]])
for idx in range(self.test_data.shape[0]/self.batch_size):
batch_images = self.test_data[idx*self.batch_size:(idx+1)*self.batch_size, :-1]
start = time.time()
prob = self.forward(batch_images)
end = time.time()
print("inferencing time: %f"%(end-start))
pred_labels = np.argmax(prob, axis=1)
pred_results[idx*self.batch_size:(idx+1)*self.batch_size] = pred_labels
accuracy = np.mean(pred_results == self.test_data[:,-1])
print('Accuracy in test set: %f' % accuracy)