def _lr_callback_init_policies(self, classifier_module, policy, instance,
**kwargs):
X, y = make_classification(1000, 20, n_informative=10, random_state=0)
X = X.astype(np.float32)
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(classifier_module,
max_epochs=2,
callbacks=[lr_policy])
net.fit(X, y)
assert any(
list(
map(
lambda x: isinstance(getattr(x[1], '_lr_scheduler', None),
instance), net.callbacks_)))
def test_lr_callback_batch_steps_correctly(
self,
classifier_module,
classifier_data,
policy,
kwargs,
):
num_examples = 1000
batch_size = 100
max_epochs = 2
X, y = classifier_data
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(classifier_module(), max_epochs=max_epochs,
batch_size=batch_size, callbacks=[lr_policy])
net.fit(X, y)
expected = (num_examples // batch_size) * max_epochs
# pylint: disable=protected-access
assert lr_policy.lr_scheduler_.last_batch_idx == expected
def test_lr_callback_steps_correctly(
self,
classifier_module,
classifier_data,
policy,
kwargs,
):
max_epochs = 2
X, y = classifier_data
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(
classifier_module(),
max_epochs=max_epochs,
batch_size=16,
callbacks=[lr_policy],
)
net.fit(X, y)
# pylint: disable=protected-access
assert lr_policy.lr_scheduler_.last_epoch == max_epochs - 1
def test_lr_callback_init_policies(
self,
classifier_module,
classifier_data,
policy,
instance,
kwargs,
):
X, y = classifier_data
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(
classifier_module, max_epochs=2, callbacks=[lr_policy]
)
net.fit(X, y)
assert any(list(map(
lambda x: isinstance(
getattr(x[1], 'lr_scheduler_', None), instance),
net.callbacks_
)))
def test_lr_callback_steps_correctly(
self,
classifier_module,
classifier_data,
policy,
kwargs,
):
max_epochs = 2
X, y = classifier_data
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(
classifier_module(),
max_epochs=max_epochs,
batch_size=16,
callbacks=[lr_policy],
)
net.fit(X, y)
# pylint: disable=protected-access
assert lr_policy.lr_scheduler_.last_epoch == max_epochs - 1
def test_lr_callback_init_policies(
self,
classifier_module,
classifier_data,
policy,
instance,
kwargs,
):
X, y = classifier_data
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(classifier_module,
max_epochs=2,
callbacks=[lr_policy])
net.fit(X, y)
assert any(
list(
map(
lambda x: isinstance(getattr(x[1], 'lr_scheduler_', None),
instance), net.callbacks_)))
def test_lr_callback_batch_steps_correctly(
self,
classifier_module,
classifier_data,
policy,
kwargs,
):
num_examples = 1000
batch_size = 100
max_epochs = 2
X, y = classifier_data
lr_policy = LRScheduler(policy, **kwargs)
net = NeuralNetClassifier(classifier_module(),
max_epochs=max_epochs,
batch_size=batch_size,
callbacks=[lr_policy])
net.fit(X, y)
expected = (num_examples // batch_size) * max_epochs
# pylint: disable=protected-access
assert lr_policy.lr_scheduler_.last_batch_idx == expected
def __init__(self):
super().__init__()
self.layer1 = torch.nn.Linear(21, 17)
self.layer2 = torch.nn.Linear(17, 13)
self.layer3 = torch.nn.Linear(13, 9)
self.layer4 = torch.nn.Linear(9, 5)
self.dropout = torch.nn.Dropout(0.5)
def forward(self, x):
out1 = F.relu(self.layer1(x))
out1 = self.dropout(out1)
out2 = F.relu(self.layer2(out1))
out3 = F.relu(self.layer3(out2))
y_pred = F.softmax(self.layer4(out3))
return y_pred.float()
net = NeuralNetClassifier(
Model,
max_epochs=1000,
lr=0.01
# use_cuda=True, # uncomment this to train with CUDA
)
pipe = Pipeline([
('scale', StandardScaler()),
('net', net),
])
pipe.fit(X, y)
x = x.view(in_size, -1) # flatten the tensor
x = self.fc1(x)
x = F.relu(x)
x = self.fc2(x)
x = F.softmax(x)
return x
nnet = NeuralNetClassifier(
module=Net,
max_epochs=10,
lr=0.06,
criterion=nn.NLLLoss,
optimizer=torch.optim.SGD,
optimizer_momentum=0.9,
)
# nnet=Net()
# print(X)
# print(Ytrain)
X = X.astype(np.float32)
Ytrain = Ytrain.astype(np.int64)
print(type(X))
print(type(Ytrain))
print(type(X[0]))
print(type(X[0][0]))
self.fc2 = nn.Linear(128, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, x.size(1) * x.size(2) * x.size(3)) # flatten over channel, height and width = 1600
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
x = F.softmax(x, dim=-1)
return x
cnn = NeuralNetClassifier(
Cnn,
max_epochs=8,
lr=1,
optimizer=torch.optim.Adadelta,
# device='cuda', # uncomment this to train with CUDA
)
#train the module
cnn.fit(XCnn_train, y_train);
#Use validation set to see the accuracy
cnn_pred = cnn.predict(XCnn_test)
print(np.mean(cnn_pred == y_test))
#predict the test set
cnn_pred_test = cnn.predict(test)
# In[80]:
#write to .csv file
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(28 * 28,num)
self.fc2 = nn.Linear(num, 20)
def forward(self, X, **kwargs):
X = F.sigmoid(self.fc1(X))
X = F.softmax(self.fc2(X))
return X
nnet=NeuralNetClassifier(
Net,
max_epochs=20,
lr=0.0165,
criterion=nn.NLLLoss,
optimizer=torch.optim.SGD,
)
print(X)
print(Ytrain)
X = X.astype(np.float32)
Ytrain = Ytrain.astype(np.int64)
print(type(X))
print(type(Ytrain))
print(type(X[0]))
module1 = MyModule1()
module2 = MyModule2()
#这样子，我先把下面的东西理顺，再说和上面相结合的问题咯。
net = NeuralNetClassifier(
module=module1,
lr=0.1,
#原来这里并不是GPU而是cuda呀S
#好像pytorch版本框架二报错是因为cuda
device="cuda",
#device="cpu",
max_epochs=10,
#criterion=torch.nn.NLLLoss,
optimizer=torch.optim.Adam,
criterion=torch.nn.CrossEntropyLoss,
#http://skorch.readthedocs.io/en/latest/user/neuralnet.html
#上面的链接中的callback的部分讲解了如何传入自己的callback
#然后查看net.py中的_default_callbacks函数能够知道如何实现函数
#最后一个细节是如何打断训练，我现在查阅过max_epochs以及KeyboardInterrupt并不知如何代码打断训练
#http://skorch.readthedocs.io/en/latest/callbacks.html上面有skorch.callbacks.EarlyStopping
#然而我这里并不能够发现这个库，可能是库的版本的问题，我运行skorch的安装命令就直接更新到最新版本了
#果然是更新到最新版本就可以了，从此妈妈再也不用担心我的max_epochs的需要枚举咯
#按照时间推算的话，这个skroch版本的应该是最近一个月才出来的吧，花了这么多时间总算搞定这个问题了，看看代码就完事儿了
#说真的这个东西让我自己实现起来还是挺麻烦的，主要是对于这些代码或者库的机制不够熟悉，比如说为何Checkpoint要实现_sink
callbacks=[skorch.callbacks.EarlyStopping(patience=5)])
#确定流程是否达到预期而非仅仅是能够运行
#选择合适的参数进行数据集增强最终提交模型预测结果（可能涉及到模型的保存）
#以后将特征工程进行封装形成框架三吧，这样子的话数据过来自动特征工程，然后自动数据集增强并提交结果
params = {
epochs = 200
batch_size = 16
class Mydnn(nn.Module):
def __init__(self, time_window=2, stride=2, n_elec=64):
super(Mydnn, self).__init__()
self.wavelet = Wavelet_cnn(time_window, stride)
self.conv1 = nn.Conv2d(n_elec, 128, (25, 2))
self.conv2 = nn.Conv2d(128, 256, (25, 2))
self.conv3 = nn.Conv2d(256, 512, (25, 2))
self.pool = nn.AvgPool2d((2, 1))
self.conv_class = nn.Conv2d(512, 2, (1, 1))
self.pool_class = nn.AdaptiveAvgPool2d(output_size=(1, 1))
def forward(self, x):
scalegram, _ = self.wavelet(x)
scalegram = scalegram ** 2 # power
scalegram = scalegram.transpose(1, 3) # (batch, elec, seq, level)
h = self.pool(F.relu(self.conv1(scalegram)))
h = self.pool(F.relu(self.conv2(h)))
h = self.pool(F.relu(self.conv3(h)))
h = F.softmax(self.pool_class(self.conv_class(h)).squeeze())
return h
model = NeuralNetClassifier(module=Mydnn,
max_epochs=100,
lr=1e-4)
model.fit(X_train, y_train)