Created by: wyc880622

以下是训练结果评估结果，帮忙给看下。 这是数据集有问题，还是yml有问题？麻烦百度大佬给解决一下，因为我已经训练了好几次了都这样，一直都没有预测成功。谢谢。我将数据集和yml在百度云盘上

链接：https://pan.baidu.com/s/1ZzxXC4Cpui7SEkmJ_McIpA 密码：7zfb

2020-04-26 05:37:36,427-INFO: iter: 99840, lr: 0.000100, 'loss_cls': '0.002928', 'loss_bbox': '0.000691', 'loss_rpn_cls': '0.000069', 'loss_rpn_bbox': '0.000110 ', 'loss': '0.003521', time: 1.152, eta: 0:03:04 2020-04-26 05:37:59,466-INFO: iter: 99860, lr: 0.000100, 'loss_cls': '0.002101', 'loss_bbox': '0.000775', 'loss_rpn_cls': '0.000064', 'loss_rpn_bbox': '0.000113 ', 'loss': '0.003694', time: 1.152, eta: 0:02:41 2020-04-26 05:38:22,463-INFO: iter: 99880, lr: 0.000100, 'loss_cls': '0.001806', 'loss_bbox': '0.000916', 'loss_rpn_cls': '0.000093', 'loss_rpn_bbox': '0.000110 ', 'loss': '0.002956', time: 1.150, eta: 0:02:17 2020-04-26 05:38:45,482-INFO: iter: 99900, lr: 0.000100, 'loss_cls': '0.002629', 'loss_bbox': '0.001159', 'loss_rpn_cls': '0.000064', 'loss_rpn_bbox': '0.000118 ', 'loss': '0.003804', time: 1.151, eta: 0:01:55 2020-04-26 05:39:08,502-INFO: iter: 99920, lr: 0.000100, 'loss_cls': '0.003152', 'loss_bbox': '0.000819', 'loss_rpn_cls': '0.000041', 'loss_rpn_bbox': '0.000111 ', 'loss': '0.004007', time: 1.151, eta: 0:01:32 2020-04-26 05:39:31,532-INFO: iter: 99940, lr: 0.000100, 'loss_cls': '0.003664', 'loss_bbox': '0.000775', 'loss_rpn_cls': '0.000059', 'loss_rpn_bbox': '0.000109 ', 'loss': '0.004821', time: 1.152, eta: 0:01:09 2020-04-26 05:39:54,549-INFO: iter: 99960, lr: 0.000100, 'loss_cls': '0.002765', 'loss_bbox': '0.000710', 'loss_rpn_cls': '0.000054', 'loss_rpn_bbox': '0.000101 ', 'loss': '0.003740', time: 1.151, eta: 0:00:46 2020-04-26 05:40:17,580-INFO: iter: 99980, lr: 0.000100, 'loss_cls': '0.001990', 'loss_bbox': '0.000718', 'loss_rpn_cls': '0.000073', 'loss_rpn_bbox': '0.000110 ', 'loss': '0.003247', time: 1.151, eta: 0:00:23 2020-04-26 05:40:39,423-INFO: Save model to output\faster_rcnn_r50_1x\model_fina l. 2020-04-26 05:40:42,905-INFO: Test iter 0 2020-04-26 05:41:08,299-INFO: Test finish iter 42 2020-04-26 05:41:08,299-INFO: Total number of images: 42, inference time: 1.6127 174299306581 fps. loading annotations into memory... Done (t=0.00s) creating index... index created! 2020-04-26 05:41:08,305-INFO: Start evaluate... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type bbox DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.01s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000

Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000

Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000 2020-04-26 05:41:08,332-INFO: Best test box ap: 6.387735547748324e-05, in iter: 4000

(paddle) E:\paddle\PaddleDetection-release-0.2>python -u tools/infer.py -c confi gs/faster_rcnn_r50_1x.yml -o weights=output\faster_rcnn_r50_1x\best_model --infe r_img=demo/1.jpg --output_dir=infer_output W0426 11:01:37.559897 5576 device_context.cc:237] Please NOTE: device: 0, CUDA Capability: 61, Driver API Version: 10.2, Runtime API Version: 10.0 W0426 11:01:37.568897 5576 device_context.cc:245] device: 0, cuDNN Version: 7.5 . 2020-04-26 11:01:38,493-INFO: Loading parameters from output\faster_rcnn_r50_1x
best_model... 2020-04-26 11:01:40,755-INFO: Load categories from E:/paddle/PaddleDetection-rel ease-0.2/dataset/coco/annotations/instance_test.json loading annotations into memory... Done (t=0.00s) creating index... index created! 2020-04-26 11:01:42,005-INFO: Infer iter 0 2020-04-26 11:01:42,014-INFO: Detection bbox results save in infer_output\1.jpg