3.2.7训练模型 代码bug about dive-into-dl-pytorch HOT 1 CLOSED

把前面生成模型的features和labels+= 转换成float32格式完美解决
######float64和32报错
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.from_numpy(np.random.normal(0, 1, (num_examples, num_inputs)))
features = features.to(torch.float32)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
dd = torch.from_numpy(np.random.normal(0, 0.01, size=labels.size()))
dd = dd.to(torch.float32)
labels += dd
features[0],labels[0]
#####或者是
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.randn(num_examples, num_inputs)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)

from dive-into-dl-pytorch.