RuntimeError: cannot perform reduction function max on tensor with no elements because the operation does not have an identity

[A154609]

n main() File "train.py", line 105, in main model = train(cfg, args) File "train.py", line 44, in train model = do_train(cfg, model, train_loader, optimizer, scheduler, checkpointer, device, arguments, args) File "E:\A开源代码\SSD-master1\SSD-master\ssd\engine\trainer.py", line 76, in dotrain for iteration, (images, targets, ) in enumerate(data_loader, start_iter): File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 363, in next data = self._next_data() File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 989, in _next_data return self._process_data(data) File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 1014, in _process_data data.reraise() File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch_utils.py", line 395, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in DataLoader worker process 2. Original Traceback (most recent call last): File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data_utils\worker.py", line 185, in _worker_loop data = fetcher.fetch(index) File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "E:\A开源代码\SSD-master1\SSD-master\ssd\data\datasets\voc.py", line 42, in getitem boxes, labels = self.target_transform(boxes, labels) File "E:\A开源代码\SSD-master1\SSD-master\ssd\data\transforms\target_transform.py", line 20, in call boxes, labels = box_utils.assign_priors(gt_boxes, gt_labels, self.corner_form_priors, self.iou_threshold) File "E:\A开源代码\SSD-master1\SSD-master\ssd\utils\box_utils.py", line 93, in assign_priors best_target_per_prior, best_target_per_prior_index = ious.max(1) RuntimeError: cannot perform reduction function max on tensor with no elements because the operation does not have an identity

(pytorch) E:\A开源代码\SSD-master1\SSD-master>

[xhpk]

n main() File "train.py", line 105, in main model = train(cfg, args) File "train.py", line 44, in train model = do_train(cfg, model, train_loader, optimizer, scheduler, checkpointer, device, arguments, args) File "E:\A开源代码\SSD-master1\SSD-master\ssd\engine\trainer.py", line 76, in dotrain for iteration, (images, targets, ) in enumerate(data_loader, start_iter): File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 363, in next data = self._next_data() File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 989, in _next_data return self._process_data(data) File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 1014, in _process_data data.reraise() File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch_utils.py", line 395, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in DataLoader worker process 2. Original Traceback (most recent call last): File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data_utils\worker.py", line 185, in _worker_loop data = fetcher.fetch(index) File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "E:\A开源代码\SSD-master1\SSD-master\ssd\data\datasets\voc.py", line 42, in getitem boxes, labels = self.target_transform(boxes, labels) File "E:\A开源代码\SSD-master1\SSD-master\ssd\data\transforms\target_transform.py", line 20, in call boxes, labels = box_utils.assign_priors(gt_boxes, gt_labels, self.corner_form_priors, self.iou_threshold) File "E:\A开源代码\SSD-master1\SSD-master\ssd\utils\box_utils.py", line 93, in assign_priors best_target_per_prior, best_target_per_prior_index = ious.max(1) RuntimeError: cannot perform reduction function max on tensor with no elements because the operation does not have an identity

(pytorch) E:\A开源代码\SSD-master1\SSD-master>

这个问题可能和你的label缺失有关

[A154609]

n main（） 在主 模型中的文件“ train.py”，第105行=火车（cfg，args） 在火车 模型中的文件“ train.py”，第44行，在火车模型= do_train（cfg，模型，train_loader，优化器，调度程序，检查 指针，设备，参数，参数）文件“ E：\ A开源代码\ SSD-master1 \ SSD-master \ ssd \ engine \ trainer.py”，行76，在dotrain中 进行迭代（（图像，目标，））枚举（data_loader，start_iter）： 文件“ D：\ Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch \ utils \ data \ dataloader.py”，第363行，下一个 数据= self._next_data（） 文件“ D ：_Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch \ utils \ data \ dataloader.py“，行_next_data中的 返回self._process_data（data） _process_data data.reraise（） 文件中的文件“ D：\ Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch \ utils \ data \ dataloader.py”，行（14 ）文件“ D：\ Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch_utils.py“，行395，重新 引发self.exc_type（msg） RuntimeError：在DataLoader工作进程2中捕获RuntimeError。 原始回溯（最近一次调用）： 文件” D：\ Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch \ utils \ data_utils \ worker.py“，第185行，在_worker_loop中 data = fetcher.fetch（index） 文件” D：\ Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch \ utils \ data_utils \ fetch.py​​“，第44行，在fetch data = [self.dataset [idx]中，可能是_batched_index中的idx] 文件“ D：\ Anaconda3 \ envs \ pytorch \ lib \ site-packages \ torch \ utils \ data_utils \ fetch.py​​”，第44行， 数据= [self.dataset [idx]，可能用于_batched_index中的idx]， 文件“ E： \ A开源代码\ SSD-master1 \ SSD-master \ ssd \ data \ datasets \ voc.py”，第42行，在getitem 框中，标签= self.target_transform（框，标签）， 文件“ E：\ A开源代码\ SSD-master1 \ SSD-master \ ssd \ data \ transforms \ target_transform.py“，第20行，在呼叫 框中，标签= box_utils.assign_priors（gt_boxes，gt_labels，self.corner_form_priors，self.iou_threshold） 文件” E：\ A开源代码\ SSD-master1 \ SSD-master \ ssd \ utils \ box_utils.py”，第93行，位于assign_priors best_target_per_prior，best_target_per_prior_index = ious.max（1）中 RuntimeError：无法在没有元素的张量上执行最大归约函数，因为该操作没有身份 （pytorch）E：\ A开源代码\ SSD-master1 \ SSD-master>

这个问题可能和你的标签缺失有关

我把报错的标注文件输出后，组成了一个小的训练集是可以实现训练，请问有什么办法可以检查错误的地方吗

[sunmooncode]

请问问题解决了吗！