说明此时需要float型数据，但识别到long型数据,此时需要对入参和出参做一下类型转换
output=output.to(torch.float32)
target=target.to(torch.float32)
例证如下：
output =net(input)
target = variable(t.arange(0,10))
#the point
output=output.to(torch.float32)
target=target.to(torch.float32)
criterion = nn.MSELoss()
loss = criterion(output,target)
net.zero_grad()
print("反向传播之前conv1.bias的梯度")
print(net.conv1.bias.grad)
loss.backward() #此处疑难杂症 先跳过
print("反向传播之后conv1.bias的梯度")
print(net.conv1.bias.grad)
说明此时需要float型数据，但识别到long型数据,此时需要对入参和出参做一下类型转换 例证如下：
1. install numpy found a problem: RuntimeError: Running c...
测试飞浆paddle，报错：RuntimeError: cublas64_100.dll not found问题：...
I haven't found problems about moments for a long time, a...
Recently, well actually that was long time ago,I found my...
前言 问题1 No implementation found for long com.autonavi.amap...
“I wrote a long love letter to you because i found it too...
一、创建ndarry obj.astype(dtype):转化其他detype obj.reshape(a,b):...
1.torch.cat时dim设置错误 torch.cat((a,b),1) RuntimeError: inco...
A=9B=5 A CNT=7 B. typedef struct{long idx;long x[4];}a...
本文标题：RuntimeError: Found dtype Long b
本文链接：https://www.haomeiwen.com/subject/rirlbktx.html
网友评论