Tianxiaomo / pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4
Apache License 2.0
4.47k stars 1.49k forks source link

RuntimeWarning: overflow encountered in multiply. DefaultCPUAllocator: not enough memory: you tried to allocate 4435968 bytes. Buy new RAM! #468

Open shenhaibb opened 3 years ago

shenhaibb commented 3 years ago

D:\Program Files (x86)\shenhaibb\pytorch-YOLOv4-master\train.py:504: RuntimeWarning: overflow encountered in multiply boxes[..., 1] = boxes[..., 1] img_height D:\Program Files (x86)\shenhaibb\pytorch-YOLOv4-master\train.py:506: RuntimeWarning: overflow encountered in multiply boxes[..., 3] = boxes[..., 3] img_height Epoch 1/50: 100%|█| 4952/4952 [1:26:27<00:00, 1.0 Traceback (most recent call last): File "D:\Program Files (x86)\shenhaibb\pytorch-YOLOv4-master\train.py", line 622, in train(model=model, File "D:\Program Files (x86)\shenhaibb\pytorch-YOLOv4-master\train.py", line 429, in train evaluator = evaluate(eval_model, val_loader, config, device) File "C:\Users\LYH\anaconda3\envs\pytroch1\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "D:\Program Files (x86)\shenhaibb\pytorch-YOLOv4-master\train.py", line 483, in evaluate model_input = torch.from_numpy(model_input).div(255.0) RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:75] data. DefaultCPUAllocator: not enough memory: you tried to allocate 4435968 bytes. Buy new RAM!