with torch.autograd.profiler.profile(enabled=True, use_npu=True, record_shapes=False, profile_memory=False) as prof:
pred = self.net(X)
prof.export_chrome_trace('./resnet_profile.json')
我发现它运行的时间实在是太长了！并且大部分时间都在进行矩阵乘法！
以下是我的 pytorch 网络：
class Model(torch.nn.Module):
# 构建模型（简单的卷积神经网络）
def __init__(self):
super().__init__()
# 1,28x28
self.conv1 = nn.Conv2d(1, 10, 5) # 10, 24x24
self.conv2 = nn.Conv2d(10, 20, 3) # 128, 10x10
self.fc1 = nn.Linear(20 * 10 * 10, 500)
self.fc2 = nn.Linear(500, 10)
def forward(self, x):
in_size = x.size(0)ss
out = self.conv1(x) # 24
out = F.relu(out)
out = F.max_pool2d(out, 2, 2) # 12
out = self.conv2(out) # 10
out = F.relu(out)
out = out.view(in_size, -1) # 展开成一维，方便进行FC
out = self.fc1(out)
out = F.relu(out)
out = self.fc2(out)
out = F.log_softmax(out, dim=1)
return out
点赞
收藏
回复
分享
举报
设备：Ascend 910 框架：pytorch
当我使用 profiler 查看我的网络运行状态时：
with torch.autograd.profiler.profile(enabled=True, use_npu=True, record_shapes=False, profile_memory=False) as prof: pred = self.net(X) prof.export_chrome_trace('./resnet_profile.json')我发现它运行的时间实在是太长了！并且大部分时间都在进行矩阵乘法！
以下是我的 pytorch 网络：
class Model(torch.nn.Module): # 构建模型（简单的卷积神经网络） def __init__(self): super().__init__() # 1,28x28 self.conv1 = nn.Conv2d(1, 10, 5) # 10, 24x24 self.conv2 = nn.Conv2d(10, 20, 3) # 128, 10x10 self.fc1 = nn.Linear(20 * 10 * 10, 500) self.fc2 = nn.Linear(500, 10) def forward(self, x): in_size = x.size(0)ss out = self.conv1(x) # 24 out = F.relu(out) out = F.max_pool2d(out, 2, 2) # 12 out = self.conv2(out) # 10 out = F.relu(out) out = out.view(in_size, -1) # 展开成一维，方便进行FC out = self.fc1(out) out = F.relu(out) out = self.fc2(out) out = F.log_softmax(out, dim=1) return out我在 Mindspore 上也试过，也是一样特别慢，希望能给指导一下。