- 博客(4)
- 收藏
- 关注
原创 ValueError: only one element tensors can be converted to Python scalars
This occurs when I tried to convert a list of tensors to a tensor by using:torch.tensor()solve for this:torch.stack()
2019-11-13 10:12:59 2500 1
原创 pytorch中groups参数理解
在做depthwise convolution的时候,遇到了groups参数,初步理解:out_channels中,groups个共用一组weight。example:self.dw = nn.Conv2d_bn_ReLU(cin_channels, cin_channels, kernel_size=3, stride=stride, groups=c*in_channels)为dept...
2019-10-12 02:21:34 958
原创 TypeError: data type not understood
TypeError: data type not understoodReason: use a second ‘()’ to contain the dimensions in: np.zerosE.g. :a = np.zeors((1 ,2 ,3))
2019-10-02 07:31:12 224
原创 UserWarning: Implicit dimension choice for softmax has been deprecated.
UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.错误类型:pytorch升级导致不支持隐形维度改正方法:torch.nn.Softmax()||torch.nn.Softmax(dim = 0)...
2019-09-20 08:33:37 1771 1
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人