Python 在PyTorch中绘制神经网络的决策边界
我一直在尝试绘制我的神经网络的决策边界,我使用输出层中的sigmoid函数进行二元分类,但没有成功,我发现许多帖子讨论了scikit学习分类器的决策边界的绘制,而不是PyTorch中构建的神经网络。 下面是我的神经网络:Python 在PyTorch中绘制神经网络的决策边界,python,matplotlib,neural-network,pytorch,Python,Matplotlib,Neural Network,Pytorch,我一直在尝试绘制我的神经网络的决策边界,我使用输出层中的sigmoid函数进行二元分类,但没有成功,我发现许多帖子讨论了scikit学习分类器的决策边界的绘制,而不是PyTorch中构建的神经网络。 下面是我的神经网络: class NeuralNetwork(torch.nn.Module): def __init__(self): super(NeuralNetwork, self).__init__() self.fc1 = torch.nn.Linear(23, 16
class NeuralNetwork(torch.nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__()
self.fc1 = torch.nn.Linear(23, 16)
self.fc2 = torch.nn.Linear(16, 14)
self.fc3 = torch.nn.Linear(14, 10)
self.fc4 = torch.nn.Linear(10, 5)
self.fc5 = torch.nn.Linear(5, 1)
def forward(self, x):
x = torch.relu(self.fc1(x))
x = torch.relu(self.fc2(x))
x = torch.relu(self.fc3(x))
x = torch.relu(self.fc4(x))
x = torch.sigmoid(self.fc5(x))
return x
model = NeuralNetwork().double()
CUDA = torch.cuda.is_available()
if CUDA:
model.cuda()
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-2, momentum=0.9)
model_1.train()
Precision = []
Cost = []
for epoch in range(10001):
if CUDA:
inputs = X_train.cuda()
label = Y_train.cuda()
else:
inputs = X_train
label = Y_train
prediction = model_1(inputs)
loss = criterion(prediction, label)
accuracy = ((prediction > 0.5) == label).float().mean().item()
Cost.append(loss.item())
Precision.append(accuracy)
if epoch % 1000 == 0 or epoch == 30000:
print("Epoch:", epoch, ",", "Loss:", loss.item(), ",", "Accuracy:", accuracy)
# Backpropagation process
optimizer.zero_grad()
loss.backward()
optimizer.step()
model_1.eval()
X_test = torch.from_numpy(X[27000:,:])
Y_test = torch.from_numpy(y[27000:,:]).double()
with torch.no_grad():
y_pred = model_1(X_test)
print("Accuracy: ", ((y_pred > 0.5) == Y_test).float().mean().item())
以下是我试图生成类似图的尝试:
但不幸的是,我得到了以下错误:
TypeError Traceback (most recent call last)
<ipython-input-52-fb941749621a> in <module>()
1 f, ax = plt.subplots(figsize=(8, 6))
2 contour = ax.contourf(xx, yy, probs, 25, cmap="RdBu",
----> 3 vmin=0, vmax=1)
4 ax_c = f.colorbar(contour)
5 ax_c.set_label("$P(y = 1)$")
5 frames
/usr/local/lib/python3.6/dist-packages/matplotlib/contour.py in _check_xyz(self, args, kwargs)
1549 raise TypeError("Input z must be a 2D array.")
1550 elif z.shape[0] < 2 or z.shape[1] < 2:
-> 1551 raise TypeError("Input z must be at least a 2x2 array.")
1552 else:
1553 Ny, Nx = z.shape
TypeError: Input z must be at least a 2x2 array.
TypeError回溯(最近一次调用)
在()
1 f,ax=plt.子批次(图尺寸=(8,6))
2轮廓=最大轮廓f(xx,yy,probs,25,cmap=“RdBu”,
---->3 vmin=0,vmax=1)
4 ax_c=f.色条(轮廓)
5 ax_c.set_标签($P(y=1)$)
5帧
/usr/local/lib/python3.6/dist-packages/matplotlib/contour.py in_check_xyz(self、args、kwargs)
1549 raise TypeError(“输入z必须是2D数组”)
1550 elif z.shape[0]<2或z.shape[1]<2:
->1551 raise TypeError(“输入z必须至少是2x2数组。”)
1552其他:
1553 Ny,Nx=z形
TypeError:输入z必须至少是2x2数组。
我将非常感谢你的帮助,提前谢谢
TypeError Traceback (most recent call last)
<ipython-input-52-fb941749621a> in <module>()
1 f, ax = plt.subplots(figsize=(8, 6))
2 contour = ax.contourf(xx, yy, probs, 25, cmap="RdBu",
----> 3 vmin=0, vmax=1)
4 ax_c = f.colorbar(contour)
5 ax_c.set_label("$P(y = 1)$")
5 frames
/usr/local/lib/python3.6/dist-packages/matplotlib/contour.py in _check_xyz(self, args, kwargs)
1549 raise TypeError("Input z must be a 2D array.")
1550 elif z.shape[0] < 2 or z.shape[1] < 2:
-> 1551 raise TypeError("Input z must be at least a 2x2 array.")
1552 else:
1553 Ny, Nx = z.shape
TypeError: Input z must be at least a 2x2 array.