return torch.batch_norm( RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR

时间: 2023-08-15 11:05:29 浏览: 62
这个错误通常是由于与cuDNN库相关的问题引起的。cuDNN是用于加速深度学习模型训练和推理的库。 首先,你可以尝试更新你的cuDNN库到最新版本,以确保你使用的是最新的修复和功能。 如果更新cuDNN库没有解决问题,你可以尝试以下方法: 1. 检查你的CUDA版本是否与cuDNN版本兼容。不同版本之间可能存在不兼容性。你可以查看cuDNN的文档或者CUDA的兼容性矩阵来确认版本兼容性。 2. 检查你的GPU驱动程序是否是最新版本。旧的驱动程序有时会导致与cuDNN的兼容性问题。 3. 如果你使用的是PyTorch,尝试使用不同的版本。有时候特定的PyTorch版本会与cuDNN不兼容,尝试不同的版本可能会解决问题。 4. 检查你的代码是否有其他与cuDNN相关的错误。确保你正确地设置了模型和数据,没有其他导致cuDNN错误的问题。 如果以上方法都没有解决问题,你可以尝试在PyTorch中禁用cuDNN并使用CPU进行计算。这可以通过设置环境变量`CUDA_VISIBLE_DEVICES`为一个无效的设备索引来实现,例如`export CUDA_VISIBLE_DEVICES=-1`。 如果问题仍然存在,可能需要更详细的调试信息来确定问题的根本原因。你可以查看错误堆栈跟踪以及其他相关日志信息,以便更好地理解问题所在。
相关问题

return torch.batch_norm( RuntimeError: CUDA error: out of memory

出现"RuntimeError: CUDA out of memory"错误是因为GPU显存内存不足。解决方法有以下几种: 1. 将batch_size改小:通过减小每个batch的大小,减少GPU显存的占用量。 2. 使用item()属性获取torch变量的标量值:在取出torch变量的标量值时,使用item()方法而不是直接输出变量本身,可以释放掉一些显存。 3. 添加代码以在测试阶段释放显存:在进行模型测试时,可以添加一些释放显存的代码,例如使用 torch.cuda.empty_cache() 来清理缓存。 如果需要同时利用其他GPU设备,可以按照以下方法进行配置: 1. 使用特定的GPU设备:可以使用 os.environ['CUDA_VISIBLE_DEVICES'] = "2" 来指定使用的GPU设备编号。 2. 使用多GPU并行处理:可以使用 torch.nn.DataParallel(model, device_ids=) 来指定多GPU并行处理时使用的设备编号。 请注意,在以上解决方法中,具体的设备编号和配置方式可能因实际情况不同而有所不同。

return torch.batch_norm( RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (

该报错是因为在运行中发现有至少两个设备,cuda:0和cpu上的张量。解决方法是将所有张量都放在同一个设备上运行,可以将其都改为在GPU上运算。 参考代码中没有提到具体的函数调用`return torch.batch_norm()`,所以无法针对该代码提供具体解决方法。如果你能提供更多关于这个报错的上下文信息,我可以为你提供更准确的解答。

相关推荐

pytorch代码如下:class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s if weight is not None: weight = torch.FloatTensor(weight).cuda() self.weight = weight self.cls_num_list = cls_num_list def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(1,0)) # 0,1 batch_m = batch_m.view((-1, 1)) # size=(batch_size, 1) (-1,1) x_m = x - batch_m output = torch.where(index, x_m, x) if self.weight is not None: output = output * self.weight[None, :] logit = output * self.s return F.cross_entropy(logit, target, weight=self.weight) classes=7, cls_num_list = np.zeros(classes) for , label in train_loader.dataset: cls_num_list[label] += 1 criterion_train = LDAMLoss(cls_num_list=cls_num_list, max_m=0.5, s=30) criterion_val = LDAMLoss(cls_num_list=cls_num_list, max_m=0.5, s=30) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) # 3、将数据输入mixup_fn生成mixup数据 samples, targets = mixup_fn(data, target) targets = torch.tensor(targets).to(torch.long) # 4、将上一步生成的数据输入model,输出预测结果,再计算loss output = model(samples) # 5、梯度清零(将loss关于weight的导数变成0) optimizer.zero_grad() # 6、若使用混合精度 if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm(model.parameters(), CLIP_GRAD) # 梯度裁剪,防止梯度爆炸 scaler.step(optimizer) # 更新下一次迭代的scaler scaler.update() 报错:File "/home/adminis/hpy/ConvNextV2_Demo/models/losses.py", line 53, in forward return F.cross_entropy(logit, target, weight=self.weight) File "/home/adminis/anaconda3/envs/wln/lib/python3.9/site-packages/torch/nn/functional.py", line 2824, in cross_entropy return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index) RuntimeError: multi-target not supported at /pytorch/aten/src/THCUNN/generic/ClassNLLCriterion.cu:15

pytorch部分代码如下:train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) # 3、将数据输入mixup_fn生成mixup数据 samples, targets = mixup_fn(data, target) # 4、将上一步生成的数据输入model,输出预测结果,再计算loss output = model(samples) # 5、梯度清零(将loss关于weight的导数变成0) optimizer.zero_grad() # 6、若使用混合精度 if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks or global_forward_hooks or global_forward_pre_hooks): return forward_call(*input, **kwargs) class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s self.weight = weight def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) target = torch.clamp(target, 0, index.size(1) - 1) index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) x_m = x - batch_m output = torch.where(index, x_m, x) return F.cross_entropy(self.s*output, target, weight=self.weight) 报错:RuntimeError: Expected index [112, 1] to be smaller than self [16, 7] apart from dimension 1 帮我看看如何修改源代码

pytorch部分代码如下:train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) # 3、将数据输入mixup_fn生成mixup数据 samples, targets = mixup_fn(data, target) # 4、将上一步生成的数据输入model,输出预测结果,再计算loss output = model(samples) # 5、梯度清零(将loss关于weight的导数变成0) optimizer.zero_grad() # 6、若使用混合精度 if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks or global_forward_hooks or global_forward_pre_hooks): return forward_call(input, **kwargs) class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s self.weight = weight def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) x_m = x - batch_m output = torch.where(index, x_m, x) return F.cross_entropy(self.soutput, target, weight=self.weight) 报错:RuntimeError: Expected index [112, 1] to be smaller than self [16, 7] apart from dimension 1 帮我看看如何修改源代码

pytorch部分代码如下:train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) samples, targets = mixup_fn(data, target) output = model(samples) optimizer.zero_grad() if use_amp: with torch.cuda.amp.autocast(): loss = torch.nan_to_num(criterion_train(output, targets)) scaler.scale(loss).backward() torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks or global_forward_hooks or global_forward_pre_hooks): return forward_call(*input, **kwargs) class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s self.weight = weight def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) target = torch.clamp(target, 0, index.size(1) - 1) index.scatter_(1, target.unsqueeze(1).type(torch.int64), 1) index = index[:, :x.size(1)] index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) x_m = x - batch_m output = torch.where(index, x_m, x) return F.cross_entropy(self.s*output, target, weight=self.weight) 报错: File "/home/adminis/hpy/ConvNextV2_Demo/train+ca.py", line 46, in train loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss File "/home/adminis/anaconda3/envs/wln/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/adminis/hpy/ConvNextV2_Demo/models/utils.py", line 622, in forward index.scatter_(1, target.unsqueeze(1).type(torch.int64), 1) # target.data.view(-1, 1). RuntimeError: Index tensor must have the same number of dimensions as self tensor 帮我看看如何修改源代码

pytorch部分代码如下:class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s if weight is not None: weight = torch.FloatTensor(weight).cuda() self.weight = weight self.cls_num_list = cls_num_list def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) # size=(batch_size, 1) (-1,1) x_m = x - batch_m output = torch.where(index, x_m, x) if self.weight is not None: output = output * self.weight[None, :] logit = output * self.s return F.cross_entropy(logit, target, weight=self.weight) train_loader = torch.utils.data.DataLoader(dataset_train, batch_size=BATCH_SIZE, shuffle=True,drop_last=True) test_loader = torch.utils.data.DataLoader(dataset_test, batch_size=BATCH_SIZE, shuffle=True) cls_num_list = np.zeros(classes) for , label in train_loader.dataset: cls_num_list[label] += 1 criterion_train = LDAMLoss(cls_num_list=cls_num_list, max_m=0.5, s=30) criterion_val = LDAMLoss(cls_num_list=cls_num_list, max_m=0.5, s=30) mixup_fn = Mixup( mixup_alpha=0.8, cutmix_alpha=1.0, cutmix_minmax=None, prob=0.1, switch_prob=0.5, mode='batch', label_smoothing=0.1, num_classes=classes) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) # 3、将数据输入mixup_fn生成mixup数据 samples, targets = mixup_fn(data, target) targets = torch.tensor(targets).to(torch.long) # 4、将上一步生成的数据输入model,输出预测结果,再计算loss output = model(samples) # 5、梯度清零(将loss关于weight的导数变成0) optimizer.zero_grad() # 6、若使用混合精度 if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm(model.parameters(), CLIP_GRAD) # 梯度裁剪,防止梯度爆炸 scaler.step(optimizer) # 更新下一次迭代的scaler scaler.update() # 否则,直接反向传播求梯度 else: loss = criterion_train(output, targets) loss.backward() torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) optimizer.step() 报错:RuntimeError: Expected index [112, 1] to be smaller than self [16, 7] apart from dimension 1

pytorch部分代码如下:class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s # self.weight = weight if weight is not None: weight = torch.FloatTensor(weight).cuda() self.weight = weight self.cls_num_list = cls_num_list def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) # 0,1 batch_m = batch_m.view((x.size(0), 1)) # size=(batch_size, 1) (-1,1) x_m = x - batch_m output = torch.where(index, x_m, x) # return F.cross_entropy(self.s*output, target, weight=self.weight) if self.weight is not None: output = output * self.weight[None, :] target = torch.flatten(target) # 将 target 转换成 1D Tensor logit = output * self.s return F.cross_entropy(logit, target, weight=self.weight) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) # 3、将数据输入mixup_fn生成mixup数据 samples, targets = mixup_fn(data, target) # 4、将上一步生成的数据输入model,输出预测结果,再计算loss output = model(samples) # 5、梯度清零(将loss关于weight的导数变成0) optimizer.zero_grad() loss = criterion_train(output, targets) # 6、若使用混合精度 if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 # loss = torch.nan_to_num(criterion_train(output, target_a, target_b, lam)) # 计算loss # loss = lam * criterion_train(output, target_a) + (1 - lam) * criterion_train(output, target_b) # 计算 mixup 后的损失函数 scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) # 梯度裁剪,防止梯度爆炸 scaler.step(optimizer) # 更新下一次迭代的scaler scaler.update() # 否则,直接反向传播求梯度 else: # loss = criterion_train(output, targets) loss.backward() torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) optimizer.step() 报错:) File "/home/adminis/hpy/ConvNextV2_Demo/models/losses.py", line 48, in forward output = torch.where(index, x_m, x) RuntimeError: expected scalar type float but found c10::Half

pytorch部分代码如下:train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device, non_blocking=True), Variable(target).to(device,non_blocking=True) # 3、将数据输入mixup_fn生成mixup数据 samples, targets = mixup_fn(data, target) # 4、将上一步生成的数据输入model,输出预测结果,再计算loss output = model(samples) # 5、梯度清零(将loss关于weight的导数变成0) optimizer.zero_grad() # 6、若使用混合精度 if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks or global_forward_hooks or global_forward_pre_hooks): return forward_call(*input, **kwargs) class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s self.weight = weight def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) target = torch.clamp(target, 0, index.size(1) - 1) index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) index = index[:, :x.size(1)] index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) x_m = x - batch_m output = torch.where(index, x_m, x) return F.cross_entropy(self.s*output, target, weight=self.weight) 报错:RuntimeError: Expected index [112, 1] to be smaller than self [16, 7] apart from dimension 1 帮我看看如何修改源代码

pytorch部分代码如下:train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks or global_forward_hooks or global_forward_pre_hooks): return forward_call(*input, **kwargs) class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s self.weight = weight def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) x_m = x - batch_m output = torch.where(index, x_m, x) return F.cross_entropy(self.s*output, target, weight=self.weight) 报错:Traceback (most recent call last): File "/home/adminis/hpy/ConvNextV2_Demo/train+ca.py", line 279, in <module> train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) File "/home/adminis/hpy/ConvNextV2_Demo/train+ca.py", line 46, in train loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss File "/home/adminis/anaconda3/envs/wln/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in call_impl return forward_call(*input, **kwargs) File "/home/adminis/hpy/ConvNextV2_Demo/models/utils.py", line 621, in forward index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) RuntimeError: Expected index [112, 1] to be smaller than self [16, 7] apart from dimension 1

pytorch部分代码如下:train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) if use_amp: with torch.cuda.amp.autocast(): # 开启混合精度 loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss scaler.scale(loss).backward() # 梯度放大 torch.nn.utils.clip_grad_norm_(model.parameters(), CLIP_GRAD) if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks or global_forward_hooks or global_forward_pre_hooks): return forward_call(input, **kwargs) class LDAMLoss(nn.Module): def init(self, cls_num_list, max_m=0.5, weight=None, s=30): super(LDAMLoss, self).init() m_list = 1.0 / np.sqrt(np.sqrt(cls_num_list)) m_list = m_list * (max_m / np.max(m_list)) m_list = torch.cuda.FloatTensor(m_list) self.m_list = m_list assert s > 0 self.s = s self.weight = weight def forward(self, x, target): index = torch.zeros_like(x, dtype=torch.uint8) index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) index_float = index.type(torch.cuda.FloatTensor) batch_m = torch.matmul(self.m_list[None, :], index_float.transpose(0,1)) batch_m = batch_m.view((-1, 1)) x_m = x - batch_m output = torch.where(index, x_m, x) return F.cross_entropy(self.soutput, target, weight=self.weight) 报错:Traceback (most recent call last): File "/home/adminis/hpy/ConvNextV2_Demo/train+ca.py", line 279, in <module> train_loss, train_acc = train(model_ft, DEVICE, train_loader, optimizer, epoch,model_ema) File "/home/adminis/hpy/ConvNextV2_Demo/train+ca.py", line 46, in train loss = torch.nan_to_num(criterion_train(output, targets)) # 计算loss File "/home/adminis/anaconda3/envs/wln/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in call_impl return forward_call(*input, **kwargs) File "/home/adminis/hpy/ConvNextV2_Demo/models/utils.py", line 621, in forward index.scatter(1, target.data.view(-1, 1).type(torch.int64), 1) RuntimeError: Expected index [112, 1] to be smaller than self [16, 7] apart from dimension 1 帮我看看如何修改

File "/home/zrb/anaconda3/envs/open-mmlab/bin/mmskl", line 7, in <module> exec(compile(f.read(), __file__, 'exec')) File "/home/zrb/mmskeleton/tools/mmskl", line 123, in <module> main() File "/home/zrb/mmskeleton/tools/mmskl", line 117, in main call_obj(**cfg.processor_cfg) File "/home/zrb/mmskeleton/mmskeleton/utils/importer.py", line 24, in call_obj return import_obj(type)(**kwargs) File "/home/zrb/mmskeleton/mmskeleton/processor/recognition.py", line 47, in test output = model(data) File "/home/zrb/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/home/zrb/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 150, in forward return self.module(*inputs[0], **kwargs[0]) File "/home/zrb/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/home/zrb/mmskeleton/mmskeleton/models/backbones/st_gcn_aaai18.py", line 94, in forward x = self.data_bn(x) File "/home/zrb/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__ result = self.forward(*input, **kwargs) File "/home/zrb/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/batchnorm.py", line 81, in forward exponential_average_factor, self.eps) File "/home/zrb/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/functional.py", line 1656, in batch_norm training, momentum, eps, torch.backends.cudnn.enabled RuntimeError: running_mean should contain 60 elements not 54

最新推荐

recommend-type

ansys maxwell

ansys maxwell
recommend-type

matlab基于不确定性可达性优化的自主鲁棒操作.zip

matlab基于不确定性可达性优化的自主鲁棒操作.zip
recommend-type

pytest-2.8.0.zip

文件操作、数据分析和网络编程等。Python社区提供了大量的第三方库,如NumPy、Pandas和Requests,极大地丰富了Python的应用领域,从数据科学到Web开发。Python库的丰富性是Python成为最受欢迎的编程语言之一的关键原因之一。这些库不仅为初学者提供了快速入门的途径,而且为经验丰富的开发者提供了强大的工具,以高效率、高质量地完成复杂任务。例如,Matplotlib和Seaborn库在数据可视化领域内非常受欢迎,它们提供了广泛的工具和技术,可以创建高度定制化的图表和图形,帮助数据科学家和分析师在数据探索和结果展示中更有效地传达信息。
recommend-type

信息安全课程实验C++实现DES等算法源代码

信息安全课程实验C++实现DES等算法源代码
recommend-type

基于知识图谱的医疗诊断知识问答系统python源码+项目说明.zip

环境 python >= 3.6 pyahocorasick==1.4.2 requests==2.25.1 gevent==1.4.0 jieba==0.42.1 six==1.15.0 gensim==3.8.3 matplotlib==3.1.3 Flask==1.1.1 numpy==1.16.0 bert4keras==0.9.1 tensorflow==1.14.0 Keras==2.3.1 py2neo==2020.1.1 tqdm==4.42.1 pandas==1.0.1 termcolor==1.1.0 itchat==1.3.10 ahocorasick==0.9 flask_compress==1.9.0 flask_cors==3.0.10 flask_json==0.3.4 GPUtil==1.4.0 pyzmq==22.0.3 scikit_learn==0.24.1 效果展示 为能最简化使用该系统,不需要繁杂的部署各种七七八八的东西,当前版本使用的itchat将问答功能集成到微信做演示,这需要你的微信能登入网页微信才能使用itchat;另外对话上下文并没
recommend-type

zigbee-cluster-library-specification

最新的zigbee-cluster-library-specification说明文档。
recommend-type

管理建模和仿真的文件

管理Boualem Benatallah引用此版本:布阿利姆·贝纳塔拉。管理建模和仿真。约瑟夫-傅立叶大学-格勒诺布尔第一大学,1996年。法语。NNT:电话:00345357HAL ID:电话:00345357https://theses.hal.science/tel-003453572008年12月9日提交HAL是一个多学科的开放存取档案馆,用于存放和传播科学研究论文,无论它们是否被公开。论文可以来自法国或国外的教学和研究机构,也可以来自公共或私人研究中心。L’archive ouverte pluridisciplinaire
recommend-type

实现实时数据湖架构:Kafka与Hive集成

![实现实时数据湖架构:Kafka与Hive集成](https://img-blog.csdnimg.cn/img_convert/10eb2e6972b3b6086286fc64c0b3ee41.jpeg) # 1. 实时数据湖架构概述** 实时数据湖是一种现代数据管理架构,它允许企业以低延迟的方式收集、存储和处理大量数据。与传统数据仓库不同,实时数据湖不依赖于预先定义的模式,而是采用灵活的架构,可以处理各种数据类型和格式。这种架构为企业提供了以下优势: - **实时洞察:**实时数据湖允许企业访问最新的数据,从而做出更明智的决策。 - **数据民主化:**实时数据湖使各种利益相关者都可
recommend-type

2. 通过python绘制y=e-xsin(2πx)图像

可以使用matplotlib库来绘制这个函数的图像。以下是一段示例代码: ```python import numpy as np import matplotlib.pyplot as plt def func(x): return np.exp(-x) * np.sin(2 * np.pi * x) x = np.linspace(0, 5, 500) y = func(x) plt.plot(x, y) plt.xlabel('x') plt.ylabel('y') plt.title('y = e^{-x} sin(2πx)') plt.show() ``` 运行这段
recommend-type

JSBSim Reference Manual

JSBSim参考手册,其中包含JSBSim简介,JSBSim配置文件xml的编写语法,编程手册以及一些应用实例等。其中有部分内容还没有写完,估计有生之年很难看到完整版了,但是内容还是很有参考价值的。