Visualization of neural network structure in different frames

One 、keras

1, stay keras Use in keras.summary(), perhaps plot_model()

eg：plot_model(model,to_file="model.png",show_shapes=True,show_layer_names=True,rankdir='TB')
plt.figure(figsize=(10,10))
img = plt.imread("model.png")
plt.imshow(img)
plt.axis('off')
plt.show()

Two 、PyTorch

Output network structure ：

MyConvNet = ConvNet()
 print(MyConvNet)
#  Output results ：

ConvNet(
   (conv1): Sequential(
     (0): Conv2d(1, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
     (1): ReLU()
     (2): AvgPool2d(kernel_size=2, stride=2, padding=0)
   )
   (conv2): Sequential(
     (0): Conv2d(16, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
     (1): ReLU()
     (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
   )
   (fc): Sequential(
     (0): Linear(in_features=1568, out_features=128, bias=True)
     (1): ReLU()
     (2): Linear(in_features=128, out_features=64, bias=True)
     (3): ReLU()
   )
   (out): Linear(in_features=64, out_features=10, bias=True)
）

1, adopt HiddenLayer Visualization network

2, adopt PyTorchViz Visualization network

wait source