计算机视觉知识点-基础网络-AlexNet

1
2
3
pip install d2l==0.14.3
pip install -U mxnet-cu101mkl==1.6.0.post0  
pip install gluoncv

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
from d2l import mxnet as d2l
from mxnet import np,npx
from mxnet.gluon import nn
npx.set_np()

net = nn.Sequential()
net.add(
    nn.Conv2D(96, kernel_size=11, strides=4, activation='relu'),
    nn.MaxPool2D(pool_size=3, strides=2),
    nn.Conv2D(256, kernel_size=5, padding=2, activation='relu'),
    nn.MaxPool2D(pool_size=3, strides=2),
    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),
    nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
    nn.Dense(4096, activation='relu'), nn.Dropout(0.5),
    nn.Dense(10)
)

1
2
3
4
5
x = np.random.uniform(size=(1,1,224,224))
net.initialize()
for layer in net:
  x = layer(x)
  print(layer.name, 't', x.shape)

1
2
3
4
5
6
7
8
9
10
11
12
13
conv10 	 (1, 96, 54, 54)
pool6 	 (1, 96, 26, 26)
conv11 	 (1, 256, 26, 26)
pool7 	 (1, 256, 12, 12)
conv12 	 (1, 384, 12, 12)
conv13 	 (1, 384, 12, 12)
conv14 	 (1, 256, 12, 12)
pool8 	 (1, 256, 5, 5)
dense4 	 (1, 4096)
dropout2 	 (1, 4096)
dense5 	 (1, 4096)
dropout3 	 (1, 4096)
dense6 	 (1, 10)

1
2
batch_size=128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

1
2
lr, num_epochs = 0.01, 10
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr)

1
2
loss 0.333, train acc 0.879, test acc 0.893
4200.6 examples/sec on gpu(0)