search

JoyeZLearning / DiffDet4SAR

DiffDet4SAR: Diffusion-based Aircraft Target Detection Network for SAR Images(GRSL 2024)
Other
27 stars 3 forks source link

ValueError: cannot convert float NaN to integer #4

Closed spikeeeeeeeeee closed 1 month ago

spikeeeeeeeeee commented 4 months ago

when i use your voc2coco and modify some yaml settings, i start to train this model, but there is a problem:ValueError: cannot convert float NaN to integer i found it's beacuse the size of a image is [0, 0], but donn't know why and how to fix this bug, didi you meet this problem,?

spikeeeeeeeeee commented 4 months ago

here is details: ###################################### size is: 800 800 ###################################### size is: 0 0 /home/DiffDet4SAR-master/detectron2/data/transforms/augmentation_impl.py:192: RuntimeWarning: divide by zero encountered in scalar divide scale = size / min(h, w) /home/DiffDet4SAR-master/detectron2/data/transforms/augmentation_impl.py:196: RuntimeWarning: invalid value encountered in scalar multiply newh, neww = scale h, size ERROR [05/08 15:46:58 d2.engine.train_loop]: Exception during training: Traceback (most recent call last): File "/home/DiffDet4SAR-master/detectron2/engine/train_loop.py", line 155, in train self.run_step() File "/home/DiffDet4SAR-master/detectron2/engine/defaults.py", line 498, in run_step self._trainer.run_step() File "/home/DiffDet4SAR-master/detectron2/engine/train_loop.py", line 297, in run_step data = next(self._data_loader_iter) File "/home/DiffDet4SAR-master/detectron2/data/common.py", line 329, in iter for d in self.dataset: File "/home/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data return self._process_data(data) File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data data.reraise() File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 32, in fetch data.append(next(self.dataset_iter)) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/common.py", line 296, in iter yield self.dataset[idx] File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/common.py", line 125, in getitem data = self._map_func(self._dataset[cur_idx]) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/utils/serialize.py", line 26, in call return self._obj(args, *kwargs) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/diffusiondet/dataset_mapper.py", line 107, in call image, transforms = T.apply_transform_gens( File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 363, in apply_augmentations tfms = inputs.apply_augmentations(augmentations) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 350, in apply_augmentations return AugmentationList(augmentations)(self) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 267, in call tfm = x(aug_input) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 168, in call tfm = self.get_transform(args) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation_impl.py", line 180, in get_transform newh, neww = ResizeShortestEdge.get_output_shape(h, w, size, self.max_size) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation_impl.py", line 202, in get_output_shape newh = int(newh + 0.5) ValueError: cannot convert float NaN to integer

[05/08 15:46:58 d2.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks) [05/08 15:46:58 d2.utils.events]: iter: 0 lr: N/A max_mem: 428M Traceback (most recent call last): File "train_net.py", line 317, in launch( File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/engine/launch.py", line 84, in launch main_func(args) File "train_net.py", line 288, in main return trainer.train() File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/engine/defaults.py", line 488, in train super().train(self.start_iter, self.max_iter) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/engine/train_loop.py", line 155, in train self.run_step() File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/engine/defaults.py", line 498, in run_step self._trainer.run_step() File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/engine/train_loop.py", line 297, in run_step data = next(self._data_loader_iter) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/common.py", line 329, in iter for d in self.dataset: File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data return self._process_data(data) File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data data.reraise() File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/home/f523/anaconda3/envs/diffusiondet/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 32, in fetch data.append(next(self.dataset_iter)) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/common.py", line 296, in iter yield self.dataset[idx] File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/common.py", line 125, in getitem data = self._map_func(self._dataset[cur_idx]) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/utils/serialize.py", line 26, in call return self._obj(args, *kwargs) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/diffusiondet/dataset_mapper.py", line 107, in call image, transforms = T.apply_transform_gens( File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 363, in apply_augmentations tfms = inputs.apply_augmentations(augmentations) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 350, in apply_augmentations return AugmentationList(augmentations)(self) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 267, in call tfm = x(aug_input) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation.py", line 168, in call tfm = self.get_transform(args) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation_impl.py", line 180, in get_transform newh, neww = ResizeShortestEdge.get_output_shape(h, w, size, self.max_size) File "/home/f523/guazai/sda/ghh/DiffDet4SAR-master/detectron2/data/transforms/augmentation_impl.py", line 202, in get_output_shape newh = int(newh + 0.5) ValueError: cannot convert float NaN to integer

yangyahu-1994 commented 3 months ago

hello，have you solved this problem?

yangyahu-1994 commented 3 months ago

when i use your voc2coco and modify some yaml settings, i start to train this model, but there is a problem:ValueError: cannot convert float NaN to integer i found it's beacuse the size of a image is [0, 0], but donn't know why and how to fix this bug, didi you meet this problem,?

hello， have you solved this problem?

JoyeZLearning commented 3 months ago

Please read my README， it has been shown in details.