import sys
sys.path.append('..')
import gluonbook as gb
import mxnet as mx
from mxnet import autograd, gluon, init, nd
from mxnet.gluon import loss as gloss, nn
batch_size = 256
train_iter, test_iter = gb.load_data_fashion_mnist(batch_size)
net = nn.Sequential()
# net.add(nn.Flatten())
net.add(nn.Dense(256, activation='relu'))
net.add(nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.5})
num_epochs = 5
gb.train_cpu(net, train_iter, test_iter, loss, num_epochs, batch_size, None,
None, trainer)
# help(nd.Activation)
import sys
sys.path.append("..")
import gluonbook as gb
from mxnet import gluon, nd, autograd, init
from mxnet.gluon import loss as gloss, nn
net = nn.Sequential()
net.add(nn.Dense(128, activation='tanh'))
net.add(nn.Dense(10))
net.add(nn.Dense(10))
net.initialize(init.Normal(sigma=0.01))
batch_szie = 256
train_iter, test_iter = gb.load_data_fashion_mnist(batch_szie)
loss = gloss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.1})
epochs = 50
gb.train_cpu(net,
train_iter,
test_iter,
loss,
epochs,
batch_szie,
trainer=trainer)
b1 = nd.zeros(num_hiddens1)
W2 = nd.random.normal(scale=0.01, shape=(num_hiddens1, num_hiddens2))
b2 = nd.zeros(num_hiddens2)
W3 = nd.random.normal(scale=0.01, shape=(num_hiddens2, num_outputs))
b3 = nd.zeros(num_outputs)
params = [W1, b1, W2, b2, W3, b3]
for param in params:
param.attach_grad()
drop_prob1 = 0.2
drop_prob2 = 0.5
def net(X):
X = X.reshape(-1, num_inputs)
H1 = (nd.dot(X, W1) + b1).relu()
if autograd.is_training():
H1 = dropout(H1, drop_prob1)
H2 = (nd.dot(H1, W2) + b2).relu()
if autograd.is_training():
H2 = dropout(H2, drop_prob2)
return nd.dot(H2, W3) + b3
num_epochs = 5
lr = 0.5
batch_size = 256
loss = gloss.SoftmaxCrossEntropyLoss()
train_iter, test_iter = gb.load_data_fashion_mnist(batch_size)
gb.train_cpu(net, train_iter, test_iter, loss, num_epochs, batch_size, params,
lr)
