TF学习——TF之TFOD:基于TFOD AP训练ssd_mobilenet预模型+faster_rcnn_inception_resnet_v2_模型训练过程(TensorBoard监控)全记录(二)-阿里云开发者社区

开发者社区> 一个处女座的程序猿> 正文

TF学习——TF之TFOD:基于TFOD AP训练ssd_mobilenet预模型+faster_rcnn_inception_resnet_v2_模型训练过程(TensorBoard监控)全记录(二)

简介: TF学习——TF之TFOD:基于TFOD AP训练ssd_mobilenet预模型+faster_rcnn_inception_resnet_v2_模型训练过程(TensorBoard监控)全记录
+关注继续查看

训练过程全记录


开始


Instructions for updating:

Please switch to tf.train.get_or_create_global_step

W0929 16:09:53.723011 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/BoxEncodingPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[360]], model variable shape: [[80]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.723512 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/BoxEncodingPredictor/biases/Momentum] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[360]], model variable shape: [[80]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.725018 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/BoxEncodingPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[1536, 360]], model variable shape: [[1536, 80]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.725520 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/BoxEncodingPredictor/weights/Momentum] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[1536, 360]], model variable shape: [[1536, 80]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.729529 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[91]], model variable shape: [[21]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.730031 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/ClassPredictor/biases/Momentum] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[91]], model variable shape: [[21]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.731035 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[1536, 91]], model variable shape: [[1536, 21]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.731536 19388 variables_helper.py:141] Variable [SecondStageBoxPredictor/ClassPredictor/weights/Momentum] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[1536, 91]], model variable shape: [[1536, 21]]. This variable will not be initialized from the checkpoint.

W0929 16:09:53.733070 19388 variables_helper.py:144] Variable [global_step] is not available in checkpoint

WARNING:tensorflow:From F:\Program Files\Python\Python36\Lib\site-packages\tensorflow\contrib\slim\python\slim\learning.py:737: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.

继续16:10


Instructions for updating:

Please switch to tf.train.MonitoredTrainingSession

2018-09-29 16:10:02.301976: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2

INFO:tensorflow:Restoring parameters from voc/pretrained/model.ckpt

I0929 16:10:11.780281 19388 tf_logging.py:115] Restoring parameters from voc/pretrained/model.ckpt

INFO:tensorflow:Running local_init_op.

I0929 16:10:18.535013 19388 tf_logging.py:115] Running local_init_op.

INFO:tensorflow:Done running local_init_op.

I0929 16:10:19.400116 19388 tf_logging.py:115] Done running local_init_op.

INFO:tensorflow:Starting Session.

I0929 16:10:40.838994 19388 tf_logging.py:115] Starting Session.

INFO:tensorflow:Saving checkpoint to path voc/train_dir/model.ckpt

I0929 16:10:41.317768 19576 tf_logging.py:115] Saving checkpoint to path voc/train_dir/model.ckpt

INFO:tensorflow:Starting Queues.

I0929 16:10:41.328797 19388 tf_logging.py:115] Starting Queues.

INFO:tensorflow:global_step/sec: 0

I0929 16:10:54.108844 10952 tf_logging.py:159] global_step/sec: 0

INFO:tensorflow:Recording summary at step 0.

I0929 16:11:07.153036  1076 tf_logging.py:115] Recording summary at step 0.

INFO:tensorflow:global step 1: loss = 5.2855 (96.556 sec/step)

I0929 16:12:20.200682 19388 tf_logging.py:115] global step 1: loss = 5.2855 (96.556 sec/step)

INFO:tensorflow:global_step/sec: 0.00848223

I0929 16:12:52.110595 10952 tf_logging.py:159] global_step/sec: 0.00848223

第1、4、6、9步:16:13


INFO:tensorflow:Recording summary at step 1.

I0929 16:13:06.314384  1076 tf_logging.py:115] Recording summary at step 1.

INFO:tensorflow:global step 2: loss = 4.8016 (53.369 sec/step)

I0929 16:13:13.988794 19388 tf_logging.py:115] global step 2: loss = 4.8016 (53.369 sec/step)

INFO:tensorflow:global step 3: loss = 4.7835 (45.608 sec/step)

I0929 16:13:59.598836 19388 tf_logging.py:115] global step 3: loss = 4.7835 (45.608 sec/step)

INFO:tensorflow:global step 4: loss = 4.8204 (46.679 sec/step)

I0929 16:14:46.279041 19388 tf_logging.py:115] global step 4: loss = 4.8204 (46.679 sec/step)

INFO:tensorflow:global_step/sec: 0.0251812

I0929 16:14:51.139468 10952 tf_logging.py:159] global_step/sec: 0.0251812

INFO:tensorflow:Recording summary at step 4.

I0929 16:15:04.911759  1076 tf_logging.py:115] Recording summary at step 4.

INFO:tensorflow:global step 5: loss = 4.8758 (49.236 sec/step)

I0929 16:15:35.515572 19388 tf_logging.py:115] global step 5: loss = 4.8758 (49.236 sec/step)

INFO:tensorflow:global step 6: loss = 3.2228 (40.198 sec/step)

I0929 16:16:15.715026 19388 tf_logging.py:115] global step 6: loss = 3.2228 (40.198 sec/step)

INFO:tensorflow:global_step/sec: 0.0166681

I0929 16:16:51.128734 10952 tf_logging.py:159] global_step/sec: 0.0166681

INFO:tensorflow:Recording summary at step 6.

I0929 16:17:01.526894  1076 tf_logging.py:115] Recording summary at step 6.

INFO:tensorflow:global step 7: loss = 4.9633 (53.262 sec/step)

I0929 16:17:08.979240 19388 tf_logging.py:115] global step 7: loss = 4.9633 (53.262 sec/step)

INFO:tensorflow:global step 8: loss = 4.2235 (47.167 sec/step)

I0929 16:17:56.148062 19388 tf_logging.py:115] global step 8: loss = 4.2235 (47.167 sec/step)

INFO:tensorflow:global step 9: loss = 3.0626 (41.395 sec/step)

I0929 16:18:37.543740 19388 tf_logging.py:115] global step 9: loss = 3.0626 (41.395 sec/step)

INFO:tensorflow:global_step/sec: 0.0249998

I0929 16:18:51.130415 10952 tf_logging.py:159] global_step/sec: 0.0249998

INFO:tensorflow:Recording summary at step 9.

I0929 16:19:06.285729  1076 tf_logging.py:115] Recording summary at step 9.

INFO:tensorflow:global step 10: loss = 3.9423 (53.277 sec/step)

I0929 16:19:30.821868 19388 tf_logging.py:115] global step 10: loss = 3.9423 (53.277 sec/step)

INFO:tensorflow:global step 11: loss = 3.8488 (40.221 sec/step)

I0929 16:20:11.045604 19388 tf_logging.py:115] global step 11: loss = 3.8488 (40.221 sec/step)

INFO:tensorflow:Saving checkpoint to path voc/train_dir/model.ckpt

I0929 16:20:41.343273 19576 tf_logging.py:115] Saving checkpoint to path voc/train_dir/model.ckpt

INFO:tensorflow:global_step/sec: 0.0165616

I0929 16:20:51.891337 10952 tf_logging.py:159] global_step/sec: 0.0165616

第11~24步:16:21


INFO:tensorflow:Recording summary at step 11.

I0929 16:21:03.727980  1076 tf_logging.py:115] Recording summary at step 11.

INFO:tensorflow:global step 12: loss = 2.6101 (54.090 sec/step)

I0929 16:21:05.137731 19388 tf_logging.py:115] global step 12: loss = 2.6101 (54.090 sec/step)

INFO:tensorflow:global step 13: loss = 3.6712 (46.100 sec/step)

I0929 16:21:51.240856 19388 tf_logging.py:115] global step 13: loss = 3.6712 (46.100 sec/step)

INFO:tensorflow:global step 14: loss = 1.9164 (44.411 sec/step)

I0929 16:22:35.656246 19388 tf_logging.py:115] global step 14: loss = 1.9164 (44.411 sec/step)

INFO:tensorflow:global_step/sec: 0.0251609

I0929 16:22:51.124389 10952 tf_logging.py:159] global_step/sec: 0.0251609

INFO:tensorflow:Recording summary at step 14.

I0929 16:23:03.518480  1076 tf_logging.py:115] Recording summary at step 14.

INFO:tensorflow:global step 15: loss = 0.9196 (51.261 sec/step)

I0929 16:23:26.920724 19388 tf_logging.py:115] global step 15: loss = 0.9196 (51.261 sec/step)

INFO:tensorflow:global step 16: loss = 3.1620 (41.240 sec/step)

I0929 16:24:08.163412 19388 tf_logging.py:115] global step 16: loss = 3.1620 (41.240 sec/step)

INFO:tensorflow:global_step/sec: 0.0166543

I0929 16:24:51.213029 10952 tf_logging.py:159] global_step/sec: 0.0166543

INFO:tensorflow:Recording summary at step 16.

I0929 16:24:59.248900  1076 tf_logging.py:115] Recording summary at step 16.

INFO:tensorflow:global step 17: loss = 2.7205 (51.696 sec/step)

I0929 16:24:59.862766 19388 tf_logging.py:115] global step 17: loss = 2.7205 (51.696 sec/step)

INFO:tensorflow:global step 18: loss = 1.7422 (41.517 sec/step)

I0929 16:25:41.382816 19388 tf_logging.py:115] global step 18: loss = 1.7422 (41.517 sec/step)

INFO:tensorflow:global step 19: loss = 0.3852 (42.130 sec/step)

I0929 16:26:23.515615 19388 tf_logging.py:115] global step 19: loss = 0.3852 (42.130 sec/step)

INFO:tensorflow:global_step/sec: 0.0250171

I0929 16:26:51.131010 10952 tf_logging.py:159] global_step/sec: 0.0250171

INFO:tensorflow:Recording summary at step 19.

I0929 16:27:05.333280  1076 tf_logging.py:115] Recording summary at step 19.

INFO:tensorflow:global step 20: loss = 3.4916 (50.366 sec/step)

I0929 16:27:13.883975 19388 tf_logging.py:115] global step 20: loss = 3.4916 (50.366 sec/step)

INFO:tensorflow:global step 21: loss = 0.5574 (39.555 sec/step)

I0929 16:27:53.443298 19388 tf_logging.py:115] global step 21: loss = 0.5574 (39.555 sec/step)

INFO:tensorflow:global step 22: loss = 2.8081 (39.814 sec/step)

I0929 16:28:33.260167 19388 tf_logging.py:115] global step 22: loss = 2.8081 (39.814 sec/step)

INFO:tensorflow:global_step/sec: 0.0249801

I0929 16:28:51.226652 10952 tf_logging.py:159] global_step/sec: 0.0249801

INFO:tensorflow:Recording summary at step 22.

I0929 16:28:57.415109  1076 tf_logging.py:115] Recording summary at step 22.

INFO:tensorflow:global step 23: loss = 2.1274 (45.275 sec/step)

I0929 16:29:18.536998 19388 tf_logging.py:115] global step 23: loss = 2.1274 (45.275 sec/step)

INFO:tensorflow:global step 24: loss = 2.8762 (38.967 sec/step)

I0929 16:29:57.505466 19388 tf_logging.py:115] global step 24: loss = 2.8762 (38.967 sec/step)

INFO:tensorflow:Saving checkpoint to path voc/train_dir/model.ckpt

I0929 16:30:41.327496 19576 tf_logging.py:115] Saving checkpoint to path voc/train_dir/model.ckpt

INFO:tensorflow:Recording summary at step 24.

I0929 16:30:59.247197  1076 tf_logging.py:115] Recording summary at step 24.

INFO:tensorflow:global step 25: loss = 2.3282 (45.570 sec/step)

I0929 16:31:02.410132 19388 tf_logging.py:115] global step 25: loss = 2.3282 (45.570 sec/step)

INFO:tensorflow:global step 26: loss = 2.4746 (34.973 sec/step)

I0929 16:32:17.320121 19388 tf_logging.py:115] global step 26: loss = 2.4746 (34.973 sec/step)

经过……步骤



第168~184步:18:02


INFO:tensorflow:Recording summary at step 168.

I0929 18:02:57.965489  1076 tf_logging.py:115] Recording summary at step 168.

INFO:tensorflow:global step 169: loss = 1.0579 (39.345 sec/step)

I0929 18:03:30.128316 19388 tf_logging.py:115] global step 169: loss = 1.0579 (39.345 sec/step)

INFO:tensorflow:global step 170: loss = 1.8678 (34.187 sec/step)

I0929 18:04:04.328794 19388 tf_logging.py:115] global step 170: loss = 1.8678 (34.187 sec/step)

INFO:tensorflow:global step 171: loss = 1.3184 (35.753 sec/step)

I0929 18:04:40.097321 19388 tf_logging.py:115] global step 171: loss = 1.3184 (35.753 sec/step)

INFO:tensorflow:Recording summary at step 171.

I0929 18:05:01.107349  1076 tf_logging.py:115] Recording summary at step 171.

INFO:tensorflow:global step 172: loss = 1.8373 (42.644 sec/step)

I0929 18:05:22.745107 19388 tf_logging.py:115] global step 172: loss = 1.8373 (42.644 sec/step)

INFO:tensorflow:global step 173: loss = 0.6442 (34.338 sec/step)

I0929 18:05:57.096073 19388 tf_logging.py:115] global step 173: loss = 0.6442 (34.338 sec/step)

INFO:tensorflow:global step 174: loss = 2.1237 (36.256 sec/step)

I0929 18:06:33.718968 19388 tf_logging.py:115] global step 174: loss = 2.1237 (36.256 sec/step)

INFO:tensorflow:Recording summary at step 174.

I0929 18:06:59.115108  1076 tf_logging.py:115] Recording summary at step 174.

INFO:tensorflow:global step 175: loss = 2.0013 (42.911 sec/step)

I0929 18:07:16.632529 19388 tf_logging.py:115] global step 175: loss = 2.0013 (42.911 sec/step)

INFO:tensorflow:global step 176: loss = 0.3421 (33.903 sec/step)

I0929 18:07:50.547195 19388 tf_logging.py:115] global step 176: loss = 0.3421 (33.903 sec/step)

INFO:tensorflow:global step 177: loss = 3.3426 (31.519 sec/step)

I0929 18:08:22.122741 19388 tf_logging.py:115] global step 177: loss = 3.3426 (31.519 sec/step)

INFO:tensorflow:Recording summary at step 177.

I0929 18:08:58.772549  1076 tf_logging.py:115] Recording summary at step 177.

INFO:tensorflow:global step 178: loss = 1.3222 (41.238 sec/step)

I0929 18:09:03.364229 19388 tf_logging.py:115] global step 178: loss = 1.3222 (41.238 sec/step)

INFO:tensorflow:global step 179: loss = 0.4027 (33.960 sec/step)

I0929 18:09:37.338058 19388 tf_logging.py:115] global step 179: loss = 0.4027 (33.960 sec/step)

INFO:tensorflow:global step 180: loss = 0.6667 (34.785 sec/step)

I0929 18:10:12.152817 19388 tf_logging.py:115] global step 180: loss = 0.6667 (34.785 sec/step)

INFO:tensorflow:Saving checkpoint to path voc/train_dir/model.ckpt

I0929 18:10:41.401597 19576 tf_logging.py:115] Saving checkpoint to path voc/train_dir/model.ckpt

INFO:tensorflow:global step 181: loss = 1.0127 (36.835 sec/step)

I0929 18:10:49.260302 19388 tf_logging.py:115] global step 181: loss = 1.0127 (36.835 sec/step)

INFO:tensorflow:Recording summary at step 181.

I0929 18:11:01.773863  1076 tf_logging.py:115] Recording summary at step 181.

INFO:tensorflow:global step 182: loss = 0.4533 (42.206 sec/step)

I0929 18:11:31.493520 19388 tf_logging.py:115] global step 182: loss = 0.4533 (42.206 sec/step)

INFO:tensorflow:global step 183: loss = 0.3991 (33.720 sec/step)

I0929 18:12:05.214678 19388 tf_logging.py:115] global step 183: loss = 0.3991 (33.720 sec/step)

INFO:tensorflow:global step 184: loss = 1.1574 (33.347 sec/step)

I0929 18:12:38.562483 19388 tf_logging.py:115] global step 184: loss = 1.1574 (33.347 sec/step)

INFO:tensorflow:Recording summary at step 184.

I0929 18:13:00.190217  1076 tf_logging.py:115] Recording summary at step 184.

INFO:tensorflow:global step 185: loss = 2.0064 (41.449 sec/step)

I0929 18:13:20.013966 19388 tf_logging.py:115] global step 185: loss = 2.0064 (41.449 sec/step)

INFO:tensorflow:global step 186: loss = 1.4978 (38.620 sec/step)

I0929 18:13:58.636997 19388 tf_logging.py:115] global step 186: loss = 1.4978 (38.620 sec/step)

INFO:tensorflow:global step 187: loss = 0.2496 (36.551 sec/step)

I0929 18:14:35.188669 19388 tf_logging.py:115] global step 187: loss = 0.2496 (36.551 sec/step)

第190~202步:18:17


INFO:tensorflow:Recording summary at step 190.

I0929 18:17:01.592503  1076 tf_logging.py:115] Recording summary at step 190.

INFO:tensorflow:global step 191: loss = 1.1224 (43.398 sec/step)

I0929 18:17:22.084096 19388 tf_logging.py:115] global step 191: loss = 1.1224 (43.398 sec/step)

INFO:tensorflow:global step 192: loss = 0.8829 (35.666 sec/step)

I0929 18:17:57.750644 19388 tf_logging.py:115] global step 192: loss = 0.8829 (35.666 sec/step)

INFO:tensorflow:global step 193: loss = 2.1432 (38.027 sec/step)

I0929 18:18:35.782682 19388 tf_logging.py:115] global step 193: loss = 2.1432 (38.027 sec/step)

INFO:tensorflow:Recording summary at step 193.

I0929 18:19:02.559637  1076 tf_logging.py:115] Recording summary at step 193.

INFO:tensorflow:global step 194: loss = 1.1090 (46.321 sec/step)

I0929 18:19:22.108624 19388 tf_logging.py:115] global step 194: loss = 1.1090 (46.321 sec/step)

INFO:tensorflow:global step 195: loss = 2.5213 (34.215 sec/step)

I0929 18:19:56.324908 19388 tf_logging.py:115] global step 195: loss = 2.5213 (34.215 sec/step)

INFO:tensorflow:global step 196: loss = 2.8718 (35.261 sec/step)

I0929 18:20:31.586679 19388 tf_logging.py:115] global step 196: loss = 2.8718 (35.261 sec/step)

INFO:tensorflow:Saving checkpoint to path voc/train_dir/model.ckpt

I0929 18:20:41.404536 19576 tf_logging.py:115] Saving checkpoint to path voc/train_dir/model.ckpt

INFO:tensorflow:Recording summary at step 196.

I0929 18:21:09.099129  1076 tf_logging.py:115] Recording summary at step 196.

INFO:tensorflow:global step 197: loss = 0.6111 (48.939 sec/step)

I0929 18:21:20.526573 19388 tf_logging.py:115] global step 197: loss = 0.6111 (48.939 sec/step)

INFO:tensorflow:global step 198: loss = 1.5971 (35.082 sec/step)

I0929 18:21:55.609520 19388 tf_logging.py:115] global step 198: loss = 1.5971 (35.082 sec/step)

INFO:tensorflow:global step 199: loss = 2.2728 (35.880 sec/step)

I0929 18:22:31.491082 19388 tf_logging.py:115] global step 199: loss = 2.2728 (35.880 sec/step)

INFO:tensorflow:Recording summary at step 199.

I0929 18:23:00.506135  1076 tf_logging.py:115] Recording summary at step 199.

INFO:tensorflow:global step 200: loss = 0.7774 (42.992 sec/step)

I0929 18:23:14.495092 19388 tf_logging.py:115] global step 200: loss = 0.7774 (42.992 sec/step)

INFO:tensorflow:global step 201: loss = 1.0625 (33.835 sec/step)

I0929 18:23:48.330853 19388 tf_logging.py:115] global step 201: loss = 1.0625 (33.835 sec/step)

INFO:tensorflow:global step 202: loss = 1.9644 (33.608 sec/step)

I0929 18:24:21.939998 19388 tf_logging.py:115] global step 202: loss = 1.9644 (33.608 sec/step)

INFO:tensorflow:Recording summary at step 202.

I0929 18:25:03.530977  1076 tf_logging.py:115] Recording summary at step 202.

INFO:tensorflow:global step 203: loss = 2.2303 (47.871 sec/step)

I0929 18:25:09.812503 19388 tf_logging.py:115] global step 203: loss = 2.2303 (47.871 sec/step)

版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。

相关文章
Android开发学习之使用Toolbar实现不同的Fragment使用不同颜色的标题栏与状态栏
Android开发学习之使用Toolbar实现不同的Fragment使用不同颜色的标题栏与状态栏                                            先看效果图。
2299 0
阿里云机器学习平台DSW2:keras 模型训练与EAS部署
本文介绍如何在DSW2中使用keras训练并获取模型,然后使用eascmd指令部署模型到eas服务,最后介绍如何使用python sdk调用部署的eas服务。
1675 0
【直播】机器学习就用PAI,带你一起现场训练热狗识别模型!
看过美剧《硅谷》的同学都知道人工智能识别热狗曾是硅谷最赚钱的技术之一。去年 HBO 发布了官方的 Not Hotdog 应用,支持 iOS 和 Android 平台,据说是用 TensorFlow、Keras 和 React Native 打造的,但是源码没有公开。
1320 0
+关注
一个处女座的程序猿
国内互联网圈知名博主、人工智能领域优秀创作者,全球最大中文IT社区博客专家、CSDN开发者联盟生态成员、中国开源社区专家、华为云社区专家、51CTO社区专家、Python社区专家等,曾受邀采访和评审十多次。仅在国内的CSDN平台,博客文章浏览量超过2500万,拥有超过57万的粉丝。
1701
文章
0
问答
文章排行榜
最热
最新
相关电子书
更多
《2021云上架构与运维峰会演讲合集》
立即下载
《零基础CSS入门教程》
立即下载
《零基础HTML入门教程》
立即下载