[问题求助]
BatchNorm2d报错
【功能模块】
之前mindspore1.1.1时没有问题，mindspore版本降为1.1.0.20210101后BN层报错。
图片维度(64,3,88,88)
网络结构：
class Discriminator(nn.Cell): def __init__(self): super(Discriminator, self).__init__() self.net = nn.SequentialCell( nn.Conv2d(3, 64, kernel_size=3, padding=1,pad_mode='pad'), nn.LeakyReLU(0.2), nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1,pad_mode='pad'), nn.BatchNorm2d(64), nn.LeakyReLU(0.2), nn.Conv2d(64, 128, kernel_size=3, padding=1,pad_mode='pad'), nn.BatchNorm2d(128), nn.LeakyReLU(0.2), nn.Conv2d(128, 128, kernel_size=3, stride=2, padding=1,pad_mode='pad'), nn.BatchNorm2d(128), nn.LeakyReLU(0.2), nn.Conv2d(128, 256, kernel_size=3, padding=1,pad_mode='pad'), nn.BatchNorm2d(256), nn.LeakyReLU(0.2), nn.Conv2d(256, 256, kernel_size=3, stride=2, padding=1,pad_mode='pad'), nn.BatchNorm2d(256), nn.LeakyReLU(0.2), nn.Conv2d(256, 512, kernel_size=3, padding=1,pad_mode='pad'), nn.BatchNorm2d(512), nn.LeakyReLU(0.2), nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1,pad_mode='pad'), nn.BatchNorm2d(512), nn.LeakyReLU(0.2), nn.AvgPool2d(kernel_size=6, stride=1), nn.Conv2d(512, 1024, kernel_size=1), nn.LeakyReLU(0.2), nn.Conv2d(1024, 1, kernel_size=1) ) def construct(self, x): y=self.net(x) #print(y.shape) batch_size = x.shape[0] # print(y.view(batch_size)) sigmoid = nn.Sigmoid() return sigmoid(y.view(batch_size))
【操作步骤&问题现象】
报错：
RuntimeError: mindspore/ccsrc/backend/kernel_compiler/kernel_query.cc:95 KernelQueryAll] NotExistsError Failed to obtain operator info, Please check whether the operator info is registered, Op full name:Default/block6-ResidualBlock/bn2-BatchNorm2d/FusedBatchNorm-op27Node Type: FusedBatchNorm, Node DebugString: kernel_graph_0:0{[0]: ValueNode<Primitive> FusedBatchNorm, [1]: output, [2]: netG.block2.bn1.gamma, [3]: netG.block2.bn1.beta, [4]: netG.block2.bn1.moving_mean, [5]: netG.block2.bn1.moving_variance}
【截图信息】
【日志信息】（可选，上传日志内容或者附件）
GPU
... 查看全部