设备不一致问题 #4
Comments
|
@GDUT-ZJJ 看来这个问题仍然存在，之前在 百度贴吧 测试时都没注意到这里出错了🤣 错误堆栈运行环境 |
🎉 解决方案已找到@abandol @GDUT-ZJJ @XiuzeZhou 👋🏼 Caution 每次运行 需要修改以下部分： # 这是 MLP.ipynb 中的第8个 Python 单元格
# 对应编号 In [8]
class Net(nn.Module):
def __init__(self, feature_size=8, hidden_size=[16, 8]):
super(Net, self).__init__()
self.feature_size, self.hidden_size = feature_size, hidden_size
# 主要改动从下面开始，所有 PyTorch Tensor 或 Module 需要显式移动到目标设备上
# 否则设备将默认位于 CPU 上，疑似 @XiuzeZhou 未使用 CUDA 设备测试
self.layer0 = nn.Linear(self.feature_size, self.hidden_size[0]).to(device)
self.layers = [
nn.Sequential(
nn.Linear(self.hidden_size[i], self.hidden_size[i + 1]).to(device),
nn.ReLU().to(device),
).to(device)
for i in range(len(self.hidden_size) - 1)
]
self.linear = nn.Linear(self.hidden_size[-1], 1).to(device)
# 核心改动区域结束
def forward(self, x):
out = self.layer0(x)
for layer in self.layers:
out = layer(out)
out = self.linear(out)
return out# 这是 MLP.ipynb 的第9个 Python 单元格
# 对应编号 In [9]
def tain(
LR=0.01,
feature_size=8,
hidden_size=[16, 8],
weight_decay=0.0,
window_size=8,
EPOCH=1000,
seed=0,
):
mae_list, rmse_list, re_list = [], [], []
result_list = []
for i in range(4):
name = Battery_list[i]
train_x, train_y, train_data, test_data = get_train_test(
Battery, name, window_size
)
train_size = len(train_x)
print("sample size: {}".format(train_size))
setup_seed(seed)
# 核心改动从此处开始
model = Net(feature_size=feature_size, hidden_size=hidden_size).to(device)
optimizer = torch.optim.Adam(
model.parameters(), lr=LR, weight_decay=weight_decay
)
criterion = nn.MSELoss().to(device)
# 核心改动结束
test_x = train_data.copy()
loss_list, y_ = [0], []
for epoch in range(EPOCH):
X = np.reshape(train_x / Rated_Capacity, (-1, feature_size)).astype(
np.float32
)
y = np.reshape(train_y[:, -1] / Rated_Capacity, (-1, 1)).astype(np.float32)
X, y = torch.from_numpy(X).to(device), torch.from_numpy(y).to(device)
output = model(X)
loss = criterion(output, y)
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if (epoch + 1) % 100 == 0:
test_x = train_data.copy() # 每100次重新预测一次
point_list = []
while (len(test_x) - len(train_data)) < len(test_data):
x = np.reshape(
np.array(test_x[-feature_size:]) / Rated_Capacity,
(-1, feature_size),
).astype(np.float32)
x = torch.from_numpy(x).to(device)
pred = model(
x
) # 测试集 模型预测#pred shape为(batch_size=1, feature_size=1)
# 核心改动从此处开始
# 变量 model 和 x 均位于目标设备（GPU）上，需要将其取回 CPU
# 才能对其调用 .data 方法并进一步 .numpy() 转换为 NumPy 数组
next_point = pred.cpu().data.numpy()[0, 0] * Rated_Capacity
# 核心改动结束
test_x.append(next_point) # 测试值加入原来序列用来继续预测下一个点
point_list.append(next_point) # 保存输出序列最后一个点的预测值
y_.append(point_list) # 保存本次预测所有的预测值
loss_list.append(loss)
mae, rmse = evaluation(y_test=test_data, y_predict=y_[-1])
re = relative_error(
y_test=test_data, y_predict=y_[-1], threshold=Rated_Capacity * 0.7
)
print(
"epoch:{:<2d} | loss:{:<6.4f} | MAE:{:<6.4f} | RMSE:{:<6.4f} | RE:{:<6.4f}".format(
epoch, loss, mae, rmse, re
)
)
if (len(loss_list) > 1) and (abs(loss_list[-2] - loss_list[-1]) < 1e-5):
break
mae, rmse = evaluation(y_test=test_data, y_predict=y_[-1])
re = relative_error(
y_test=test_data, y_predict=y_[-1], threshold=Rated_Capacity * 0.7
)
mae_list.append(mae)
rmse_list.append(rmse)
re_list.append(re)
result_list.append(y_[-1])
return re_list, mae_list, rmse_list, result_list |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
您好，MLP还是有变量不在同一设备的问题。
The text was updated successfully, but these errors were encountered: