본문 바로가기

Backward

 (2)
[08] backward 과정 이해하기 for epoch in range(epochs): …… # Clear gradient buffers because we don't want any gradient from previous epoch optimizer.zero_grad() # get output from the model, given the inputs outputs = model(inputs) # get loss for the predicted output loss = criterion(outputs, labels) # get gradients w.r.t to parameters loss.backward() # update parameters optimizer.step() ……… optimizer.zero_grad() - gradient..
[02] Pytorch Basics Tensor 다차원 Arrays를 표현하는 pytorch 클래스 사실상 numpy의 ndarray와 동일 ( = 텐서프로 Tensor와 동일 ) import numpy as np n_array = np.arange(10) # array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]) n_array = n_array.reshape(2,5) print("ndim :", n_array.ndim, "shape :", n_array.shape) #ndim : 2 shape : (2, 5) import torch t_array = torch.FloatTensor(n_array) print("ndim :", t_array.ndim, "shape :", t_array.shape) # ndim : 2 shape..

티스토리툴바