LittleMio
commented
2 years ago 你好，你可以试试把numpy再降级为1.17.0，我之前也是遇到这个问题，亲测管用
Closed lhongdong closed 2 years ago
LittleMio
commented
2 years ago 你好，你可以试试把numpy再降级为1.17.0，我之前也是遇到这个问题，亲测管用
TA: 0:03:52 0%| | 0/17 [00:00<?, ?it/s]:318 - Save weights to ./YOLOX_outputs\yolox_tiny_fish 100%|##################################################################################| 17/17 [00:14<00:00, 1.20it/s] 2021-12-23 15:31:59 | INFO | yolox.evaluators.coco_evaluator:171 - Evaluate in main process... 2021-12-23 15:31:59 | INFO | yolox.evaluators.coco_evaluator:204 - Loading and preparing results... 2021-12-23 15:32:00 | INFO | yolox.evaluators.coco_evaluator:204 - DONE (t=0.06s) 2021-12-23 15:32:00 | INFO | pycocotools.coco:362 - creating index... 2021-12-23 15:32:00 | INFO | pycocotools.coco:362 - index created! 2021-12-23 15:32:00 | INFO | yolox.core.trainer:183 - Training of experiment is done and the best AP is 0.00 2021-12-23 15:32:00 | ERROR | yolox.core.launch:98 - An error has been caught in function 'launch', process 'MainProcess' (4808), thread 'MainThread' (9116): Traceback (most recent call last):
File "D:\L\Git\genshin_auto_fish\yolox_tools\train.py", line 125, in
launch(
└ <function launch at 0x000001E7F9ACB430>
File "D:\L\Git\genshin_auto_fish\yolox_tools\train.py", line 110, in main trainer.train() │ └ <function Trainer.train at 0x000001E7F9F253A0> └ <yolox.core.trainer.Trainer object at 0x000001E7FAAC7FA0>
File "d:\l\git\genshin_auto_fish\yolox\core\trainer.py", line 72, in train self.train_in_epoch() │ └ <function Trainer.train_in_epoch at 0x000001E7FAA6BE50> └ <yolox.core.trainer.Trainer object at 0x000001E7FAAC7FA0>
File "d:\l\git\genshin_auto_fish\yolox\core\trainer.py", line 82, in train_in_epoch self.after_epoch() │ └ <function Trainer.after_epoch at 0x000001E7FAA7F5E0> └ <yolox.core.trainer.Trainer object at 0x000001E7FAAC7FA0>
File "d:\l\git\genshin_auto_fish\yolox\core\trainer.py", line 207, in after_epoch self.evaluate_and_save_model() │ └ <function Trainer.evaluate_and_save_model at 0x000001E7FAA7F8B0> └ <yolox.core.trainer.Trainer object at 0x000001E7FAAC7FA0>
File "d:\l\git\genshin_auto_fish\yolox\core\trainer.py", line 302, in evaluate_and_save_model ap50_95, ap50, summary = self.exp.eval( │ │ └ <function Exp.eval at 0x000001E7FAAC69D0> │ └ ╒══════════════════╤═════════════════════════════════════════════════════════════════════════════════════════════════════════... └ <yolox.core.trainer.Trainer object at 0x000001E7FAAC7FA0>
File "d:\l\git\genshin_auto_fish\yolox\exp\yolox_base.py", line 288, in eval return evaluator.evaluate(model, is_distributed, half) │ │ │ │ └ False │ │ │ └ False │ │ └ YOLOX( │ │ (backbone): YOLOPAFPN( │ │ (backbone): CSPDarknet( │ │ (stem): Focus( │ │ (conv): BaseConv( │ │ (conv): ... │ └ <function COCOEvaluator.evaluate at 0x000001E7FAA651F0> └ <yolox.evaluators.coco_evaluator.COCOEvaluator object at 0x000001E7953392E0>
File "d:\l\git\genshin_auto_fish\yolox\evaluators\coco_evaluator.py", line 131, in evaluate eval_results = self.evaluate_prediction(data_list, statistics) │ │ │ └ tensor([ 0.9705, 0.1696, 16.0000], device='cuda:0') │ │ └ [{'image_id': 0, 'category_id': 2, 'bbox': [762.0606689453125, 391.85870361328125, 88.766845703125, 68.79165649414062], 'scor... │ └ <function COCOEvaluator.evaluate_prediction at 0x000001E7FAA65310> └ <yolox.evaluators.coco_evaluator.COCOEvaluator object at 0x000001E7953392E0>
File "d:\l\git\genshin_auto_fish\yolox\evaluators\coco_evaluator.py", line 212, in evaluate_prediction cocoEval = COCOeval(cocoGt, cocoDt, annType[1]) │ │ │ └ ['segm', 'bbox', 'keypoints'] │ │ └ <pycocotools.coco.COCO object at 0x000001E79531C850> │ └ <pycocotools.coco.COCO object at 0x000001E7FD4B5490> └ <class 'yolox.layers.fast_coco_eval_api.COCOeval_opt'>
File "D:\Anaconda3\lib\site-packages\pycocotools\cocoeval.py", line 76, in init self.params = Params(iouType=iouType) # parameters │ │ │ └ 'bbox' │ │ └ <class 'pycocotools.cocoeval.Params'> │ └ {} └ <yolox.layers.fast_coco_eval_api.COCOeval_opt object at 0x000001E7FABFC9D0>
File "D:\Anaconda3\lib\site-packages\pycocotools\cocoeval.py", line 527, in init self.setDetParams() │ └ <function Params.setDetParams at 0x000001E799E50D30> └ <pycocotools.cocoeval.Params object at 0x000001E7FABFC910>
File "D:\Anaconda3\lib\site-packages\pycocotools\cocoeval.py", line 507, in setDetParams self.iouThrs = np.linspace(.5, 0.95, np.round((0.95 - .5) / .05) + 1, endpoint=True) │ │ │ │ └ <function round_ at 0x000001E7EE14B160> │ │ │ └ <module 'numpy' from 'D:\Anaconda3\lib\site-packages\numpy\init.py'> │ │ └ <function linspace at 0x000001E7EE75C790> │ └ <module 'numpy' from 'D:\Anaconda3\lib\site-packages\numpy\init.py'> └ <pycocotools.cocoeval.Params object at 0x000001E7FABFC910>
File "<__array_function__ internals>", line 5, in linspace
File "D:\Anaconda3\lib\site-packages\numpy\core\function_base.py", line 120, in linspace num = operator.index(num) │ │ └ 10.0 │ └
└ <module 'operator' from 'D:\Anaconda3\lib\operator.py'>
TypeError: 'numpy.float64' object cannot be interpreted as an integer