¡Hola, Mundo!

This is a note from coursera lecture : https://www.coursera.org/learn/cnns-and-rnns Is CNN fully connected neural network or no? The image above is showing that left is fully connected neural network, right is not. The right image is CNN neural network. CNN is same structure as fully connected neural network but some of weight of connections are zero. So it is partially connected neural network ..

Convolution(합성곱) The step to get the result as below. (1×1) + (2×0) + (3×1) + (2×1) + (1×0) + (0×1) + (3×0) + (0×1) + (1×0) = 6 image(입력) - 3-dimension tensor, [height, width, channel]. - Height, width are the number of pixel. Kernel The 2D matrix which has the size of HTML 삽입 미리보기할 수 없는 소스 It usually (3 x 3) or (5 x 5). Steps 1. The kernel scans the image from the first to the end in order. The..

When model uses specific layers/part-Dropouts Layers, BatchNorm Layers etc, it can be turned on during the train mode, but it needs to be turned off during the evaluation mode. model.train() model.eval() Sets model in training mode: activates specific layers/part-Dropout layers etc normalisation layers1 use per-batch statistics Sets model in evaluation (inference) mode: de-activates Dropout laye..

model.parameters() It has stored W, b. It transferable to optimizer. Let's create 1 dim of input and 1 dim of output linear model. model = nn.Linear(1,1) print(model) >>> Linear(in_features=1, out_features=1, bias=True) And check it out the Weight and Bias. First value is W, second value is b. Both are subject to learning(requires_grad=True). print(list(model.parameters())) >>> [Parameter contai..

view It merely creates a view of the original tensor. Same function as reshape in numpy. -1 : It means I am not sure so I will let pytorch to decide the dimension. torch.FloatTensor([[[1.,2.],[3.,4.]],[[5.,6.],[7.,8.]]]) >>> tensor([[[1., 2.], [3., 4.]], [[5., 6.], [7., 8.]]]) t.view([-1,2]) >>> tensor([[1., 2.], [3., 4.], [5., 6.], [7., 8.]]) a=torch.randn(1,2,3,4) a >>> tensor([[[[ 0.3861, -0...