如何解决Loading and preparing results... DONE (t=0.01s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.53s). Accumulating evaluation results... Traceback (most recent call last): File "tools/train.py", line 133, in <module> main() File "tools/train.py", line 129, in main runner.train() File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1721, in train model = self.train_loop.run() # type: ignore File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/mmengine/runner/loops.py", line 102, in run self.runner.val_loop.run() File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/mmengine/runner/loops.py", line 366, in run metrics = self.evaluator.evaluate(len(self.dataloader.dataset)) File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/mmengine/evaluator/evaluator.py", line 79, in evaluate _results = metric.evaluate(size) File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/mmengine/evaluator/metric.py", line 133, in evaluate _metrics = self.compute_metrics(results) # type: ignore File "/home/wangbei/mmdetection(coco)/mmdet/evaluation/metrics/coco_metric.py", line 512, in compute_metrics coco_eval.accumulate() File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/pycocotools-2.0-py3.8-linux-x86_64.egg/pycocotools/cocoeval.py", line 378, in accumulate tp_sum = np.cumsum(tps, axis=1).astype(dtype=np.float) File "/home/wangbei/anaconda3/envs/Object_mmdetection/lib/python3.8/site-packages/numpy/__init__.py", line 305, in __getattr__ raise AttributeError(__former_attrs__[attr]) AttributeError: module 'numpy' has no attribute 'float'. `np.float` was a deprecated alias for the builtin `float`. To avoid this error in existing code, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here. The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 30235 closing signal SIGTERM ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 30234) of binary: /home/wangbei/anaconda3/envs/Object_mmdetection/bin/python
时间: 2023-10-09 11:17:31 浏览: 239
【优质】英语专八听力特殊词汇.pdf
这是一个错误日志,看起来是在运行目标检测模型时出现的。错误信息显示在使用numpy库时出现了问题,建议检查代码中是否有使用到numpy库的地方,尤其是是否有使用了np.float这个别名,如果有的话,应该使用float代替。此外,还建议检查代码中是否有使用到torch.distributed.elastic.multiprocessing.api,如果有,也需要检查相关的代码是否有问题。最后,可以尝试搜索相关错误信息,看看是否有其他开发者遇到过类似的问题并给出了解决方案。
阅读全文