摘要：打开CMD copy/b 1.jpg+2.zip 3.jpg 阅读全文

摘要：def test_onehot(): v = torch.tensor([[0.1, 0.2, 0.7], [0.1, 0.6, 0.3], [0.1, 0.5, 0.4], [0.8, 0.1, 0.1], ]) print('v', v.size(), v) # 按照形状创建全0张量 resul 阅读全文

摘要：交叉熵计算损失 import torch loss_func = torch.nn.CrossEntropyLoss() v1 = torch.tensor([[0.1, 0.7, 0.2]]) v2 = torch.tensor([[0.2, 0.3, 0.5]]) v3 = torch.tens 阅读全文