• paddleDetection train log


    paddleDetection train log

    [04/02 14:10:27] ppdet.engine INFO: Epoch: [99] [14520/14658] learning_rate: 0.000001 loss_xy: 12.273930 loss_wh: 3.473294 loss_obj: 20.448202 loss_cls: 8.252794 loss: 44.945595 eta: 0:01:04 batch_cost: 0.4589 data_cost: 0.0002 ips: 17.4342 images/s
    [04/02 14:10:36] ppdet.engine INFO: Epoch: [99] [14540/14658] learning_rate: 0.000001 loss_xy: 14.349242 loss_wh: 3.617645 loss_obj: 24.267742 loss_cls: 7.921866 loss: 47.407486 eta: 0:00:55 batch_cost: 0.4359 data_cost: 0.0002 ips: 18.3538 images/s
    [04/02 14:10:46] ppdet.engine INFO: Epoch: [99] [14560/14658] learning_rate: 0.000001 loss_xy: 11.139051 loss_wh: 3.144288 loss_obj: 16.946981 loss_cls: 7.191289 loss: 39.561420 eta: 0:00:45 batch_cost: 0.5152 data_cost: 0.0002 ips: 15.5265 images/s
    [04/02 14:10:55] ppdet.engine INFO: Epoch: [99] [14580/14658] learning_rate: 0.000001 loss_xy: 10.631355 loss_wh: 2.776225 loss_obj: 15.628025 loss_cls: 6.776411 loss: 37.904350 eta: 0:00:36 batch_cost: 0.4477 data_cost: 0.0002 ips: 17.8697 images/s
    [04/02 14:11:04] ppdet.engine INFO: Epoch: [99] [14600/14658] learning_rate: 0.000001 loss_xy: 12.825715 loss_wh: 3.540399 loss_obj: 21.935436 loss_cls: 8.111532 loss: 46.578396 eta: 0:00:27 batch_cost: 0.4439 data_cost: 0.0002 ips: 18.0203 images/s
    [04/02 14:11:15] ppdet.engine INFO: Epoch: [99] [14620/14658] learning_rate: 0.000001 loss_xy: 12.241335 loss_wh: 3.509616 loss_obj: 20.464123 loss_cls: 6.314967 loss: 43.114769 eta: 0:00:17 batch_cost: 0.5226 data_cost: 0.0002 ips: 15.3086 images/s
    [04/02 14:11:24] ppdet.engine INFO: Epoch: [99] [14640/14658] learning_rate: 0.000001 loss_xy: 11.870386 loss_wh: 3.170647 loss_obj: 19.741116 loss_cls: 7.042663 loss: 39.897247 eta: 0:00:08 batch_cost: 0.4427 data_cost: 0.0002 ips: 18.0702 images/s
    [04/02 14:11:32] ppdet.utils.checkpoint INFO: Save checkpoint: output/yolov3_darknet53_100e_coco
    [04/02 14:11:32] ppdet.engine INFO: Eval iter: 0
    [04/02 14:11:36] ppdet.engine INFO: Eval iter: 100
    [04/02 14:11:41] ppdet.engine INFO: Eval iter: 200
    [04/02 14:11:46] ppdet.engine INFO: Eval iter: 300
    [04/02 14:11:50] ppdet.engine INFO: Eval iter: 400
    [04/02 14:11:55] ppdet.engine INFO: Eval iter: 500
    [04/02 14:11:59] ppdet.engine INFO: Eval iter: 600
    [04/02 14:12:04] ppdet.engine INFO: Eval iter: 700
    [04/02 14:12:08] ppdet.engine INFO: Eval iter: 800
    [04/02 14:12:13] ppdet.engine INFO: Eval iter: 900
    [04/02 14:12:18] ppdet.engine INFO: Eval iter: 1000
    [04/02 14:12:22] ppdet.engine INFO: Eval iter: 1100
    [04/02 14:12:27] ppdet.engine INFO: Eval iter: 1200
    [04/02 14:12:31] ppdet.engine INFO: Eval iter: 1300
    [04/02 14:12:36] ppdet.engine INFO: Eval iter: 1400
    [04/02 14:12:40] ppdet.engine INFO: Eval iter: 1500
    [04/02 14:12:45] ppdet.engine INFO: Eval iter: 1600
    [04/02 14:12:49] ppdet.engine INFO: Eval iter: 1700
    [04/02 14:12:54] ppdet.engine INFO: Eval iter: 1800
    [04/02 14:12:59] ppdet.engine INFO: Eval iter: 1900
    [04/02 14:13:03] ppdet.engine INFO: Eval iter: 2000
    [04/02 14:13:08] ppdet.engine INFO: Eval iter: 2100
    [04/02 14:13:12] ppdet.engine INFO: Eval iter: 2200
    [04/02 14:13:17] ppdet.engine INFO: Eval iter: 2300
    [04/02 14:13:21] ppdet.engine INFO: Eval iter: 2400
    [04/02 14:13:26] ppdet.engine INFO: Eval iter: 2500
    [04/02 14:13:30] ppdet.engine INFO: Eval iter: 2600
    [04/02 14:13:35] ppdet.engine INFO: Eval iter: 2700
    [04/02 14:13:39] ppdet.engine INFO: Eval iter: 2800
    [04/02 14:13:44] ppdet.engine INFO: Eval iter: 2900
    [04/02 14:13:48] ppdet.engine INFO: Eval iter: 3000
    [04/02 14:13:53] ppdet.engine INFO: Eval iter: 3100
    [04/02 14:13:57] ppdet.engine INFO: Eval iter: 3200
    [04/02 14:14:02] ppdet.engine INFO: Eval iter: 3300
    [04/02 14:14:07] ppdet.engine INFO: Eval iter: 3400
    [04/02 14:14:11] ppdet.engine INFO: Eval iter: 3500
    [04/02 14:14:16] ppdet.engine INFO: Eval iter: 3600
    [04/02 14:14:20] ppdet.engine INFO: Eval iter: 3700
    [04/02 14:14:24] ppdet.engine INFO: Eval iter: 3800
    [04/02 14:14:29] ppdet.engine INFO: Eval iter: 3900
    [04/02 14:14:33] ppdet.engine INFO: Eval iter: 4000
    [04/02 14:14:38] ppdet.engine INFO: Eval iter: 4100
    [04/02 14:14:42] ppdet.engine INFO: Eval iter: 4200
    [04/02 14:14:47] ppdet.engine INFO: Eval iter: 4300
    [04/02 14:14:52] ppdet.engine INFO: Eval iter: 4400
    [04/02 14:14:56] ppdet.engine INFO: Eval iter: 4500
    [04/02 14:15:01] ppdet.engine INFO: Eval iter: 4600
    [04/02 14:15:05] ppdet.engine INFO: Eval iter: 4700
    [04/02 14:15:10] ppdet.engine INFO: Eval iter: 4800
    [04/02 14:15:14] ppdet.engine INFO: Eval iter: 4900
    [04/02 14:15:19] ppdet.metrics.metrics INFO: The bbox result is saved to bbox.json.
    loading annotations into memory...
    Done (t=0.66s)
    creating index...
    index created!
    [04/02 14:15:20] ppdet.metrics.coco_utils INFO: Start evaluate...
    Loading and preparing results...
    DONE (t=1.19s)
    creating index...
    index created!
    Running per image evaluation...
    Evaluate annotation type *bbox*
    DONE (t=32.16s).
    Accumulating evaluation results...
    DONE (t=5.02s).
     Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.328
     Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.558
     Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.345
     Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.186
     Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.358
     Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.426
     Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.277
     Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.434
     Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.454
     Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.286
     Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.482
     Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.572
    [04/02 14:15:59] ppdet.engine INFO: Total sample number: 4952, averge FPS: 21.99071245254403
    [04/02 14:15:59] ppdet.engine INFO: Best test bbox ap is 0.329.
    (wind_paddle) bim@bim-PowerEdge-R730:~/Desktop/PaddlePaddle_Project/PaddleDetection-release-2.3$ 
    (wind_paddle) bim@bim-PowerEdge-R730:~/Desktop/PaddlePaddle_Project/PaddleDetection-release-2.3$ 
    (wind_paddle) bim@bim-PowerEdge-R730:~/Desktop/PaddlePaddle_Project/PaddleDetection-release-2.3$ 

     output model:

    #######################

  • 相关阅读:
    17年day4
    11.7NOIP模拟题
    P3389 【模板】高斯消元法
    洛谷 P2136 拉近距离 题解
    浅谈SPFA判负环
    洛谷 P1629 邮递员送信 题解
    洛谷 P1821 [USACO07FEB]银牛派对Silver Cow Party 题解
    洛谷 P3905 道路重建 题解
    洛谷 P1351 联合权值 题解
    洛谷 P4779 【模板】单源最短路径(标准版) 题解
  • 原文地址:https://www.cnblogs.com/herd/p/16092709.html
Copyright © 2020-2023  润新知