# 除了最后的卷积层外，进一步增大了输出通道数
# 前两个卷积层后部使用池化层来减小输入的高和宽
nn.Conv2D(384, kernel_size=3, padding=1, activation='relu'),
nn.Conv2D(384, kernel_size=3, padding=1, activation='relu'),
nn.Conv2D(256, kernel_size=3, padding=1, activation='relu'),
nn.MaxPool2D(pool_size=3, strides=2),
# 这里全连接层的输出个数比LeNet中大数倍，使用丢弃层来缓解过拟合
nn.Dense(4096, activation='relu'),
nn.Dropout(0.5),
nn.Dense(4096, activation='relu'),
nn.Dropout(0.5),
# 输出层，对应Fashion-MNIST数据集的10种类别
nn.Dense(10))
X = nd.random.uniform(shape=(1, 1, 224, 224))
net.initialize()
for layer in net:
X = layer(X)
print(layer.name, 'output shape:\t', X.shape)
batch_size = 128
train_iter, test_iter = util.load_data_fashion_mnist(batch_size,
resize=224)
learning_rate = 0.01
num_epochs = 5
ctx = util.try_gpu()
net.initialize(force_reinit=True, ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': learning_rate})
util.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx,
num_epochs)
ratios = [[1, 2, 0.5]] * 5
num_anchors = len(sizes[0]) + len(ratios[0]) - 1
# 创建模型
net = TinySSD(num_classes=1)
net.initialize()
X = nd.zeros((32.3, 256, 256))
anchors, cls_preds, bbox_preds = net(X)
print('output anchors:', anchors.shape)
print('output class preds:', cls_preds.shape)
print('output bbox preds:', bbox_preds.shape)
# 读物数据集，初始化
batch_size = 32
train_iter, _ = util.load_data_pikachu(batch_size)
ctx, net = util.try_gpu(), TinySSD(num_classes=1)
net.initialize(init=init.Xavier(), ctx=ctx)
trainer = gluon.Trainer(net.collect_params(), 'sgd', {
'learning_rate': 0.2,
'wd': 5e-4
})
# 定义损失函数和评价函数
cls_loss = gluon.loss.SoftmaxCrossEntropyLoss()
bbox_loss = gluon.loss.L1Loss()
# 训练模型
for epoch in range(20):
acc_sum, mae_sum, n, m = 0.0, 0.0, 0, 0
train_iter.reset() # 从头读取数据
start = time.time()
if __name__ == '__main__':
block = Residual(3)
block.initialize()
X = nd.random.uniform(shape=(4, 3, 6, 6))
print(block(X).shape)
block = Residual(6, use_1x1conv=True, strides=2)
block.initialize()
print(block(X).shape)
net = nn.Sequential()
net.add(nn.Conv2D(64, kernel_size=7, padding=3, strides=2),
nn.BatchNorm(), nn.Activation('relu'),
nn.MaxPool2D(pool_size=3, padding=1, strides=2))
net.add(resnet_block(64, 2, first_block=True),
resnet_block(128, 2),
resnet_block(256, 2),
resnet_block(512, 2))
net.add(nn.GlobalAvgPool2D(), nn.Dense(10))
X = nd.random.uniform(shape=(1, 1, 224, 224))
net.initialize()
for layer in net:
X = layer(X)
print(layer.name, 'output shape:\t', X.shape)
lr, num_epochs, batch_size, ctx = 0.05, 5, 256, util.try_gpu()
net.initialize(force_reinit=True, ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
train_iter, test_iter = util.load_data_fashion_mnist(batch_size, resize=96)
util.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx, num_epochs)
nn.MaxPool2D(pool_size=3, strides=2, padding=1))
b3 = nn.Sequential()
b3.add(Inception(64, (96, 128), (16, 32), 32),
Inception(128, (128, 192), (32, 96), 64),
nn.MaxPool2D(pool_size=3, strides=2, padding=1))
b4 = nn.Sequential()
b4.add(Inception(192, (96, 208), (16, 48), 64),
Inception(160, (112, 224), (24, 64), 64),
Inception(128, (128, 256), (24, 64), 64),
Inception(112, (144, 288), (32, 64), 64),
Inception(256, (160, 320), (32, 128), 128),
nn.MaxPool2D(pool_size=3, strides=2, padding=1))
b5 = nn.Sequential()
b5.add(Inception(256, (160, 320), (32, 128), 128),
Inception(384, (192, 384), (48, 128), 128), nn.GlobalAvgPool2D())
net = nn.Sequential()
net.add(b1, b2, b3, b4, b5, nn.Dense(10))
X = nd.random.uniform(shape=(1, 1, 96, 96))
net.initialize()
for layer in net:
X = layer(X)
print(layer.name, 'output shape:\t', X.shape)
lr, num_epochs, batch_size, ctx = 0.1, 5, 128, util.try_gpu()
net.initialize(force_reinit=True, ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
train_iter, test_iter = util.load_data_fashion_mnist(batch_size, resize=96)
util.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx,
num_epochs)