我正在运行从本教程中获得的这段代码 我正在尝试运行 tensorflow 对象检测 api,所有代码运行良好,如果运行所有调用,所有单元格都会运行良好,最后,我的图像被分类。
Buuut 有 1 个不能正常工作的单元格,它可以工作,但不喜欢它必须工作。
当我用!python legacy/train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_pets.config 它训练我的模型时,它会启动 tensorflow 并开始训练,但它只运行 3 步、4 步,有时是 20、21、23 步,最后,google colab^C在此过程中设置了一个
我永远无法完成我的培训,因为 google colab 关闭了我的流程,有人知道发生了什么吗?
我已经尝试使用 GPU 和 TPU 实例。
[...]
INFO:tensorflow:Restoring parameters from training/model.ckpt-0
I1022 20:41:48.368024 139794549495680 tf_logging.py:115] Restoring parameters from training/model.ckpt-0
INFO:tensorflow:Running local_init_op.
I1022 20:41:52.779153 139794549495680 tf_logging.py:115] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I1022 20:41:52.997912 139794549495680 tf_logging.py:115] Done running local_init_op.
INFO:tensorflow:Starting Session.
I1022 20:41:59.072830 139794549495680 tf_logging.py:115] Starting Session.
INFO:tensorflow:Saving checkpoint to path training/model.ckpt
I1022 20:41:59.245162 139793493063424 tf_logging.py:115] Saving checkpoint to path training/model.ckpt
INFO:tensorflow:Starting Queues.
I1022 20:41:59.252097 139794549495680 tf_logging.py:115] Starting Queues.
INFO:tensorflow:global_step/sec: 0
I1022 20:42:10.151180 139793484670720 tf_logging.py:159] global_step/sec: 0
INFO:tensorflow:Recording summary at step 0.
I1022 20:42:16.119055 139793476278016 tf_logging.py:115] Recording summary at step 0.
INFO:tensorflow:global step 1: loss = 14.0911 (28.770 sec/step)
I1022 20:42:28.496783 139794549495680 tf_logging.py:115] global step 1: loss = 14.0911 (28.770 sec/step)
INFO:tensorflow:global step 2: loss = 12.4958 (10.529 sec/step)
I1022 20:42:39.334129 139794549495680 tf_logging.py:115] global step 2: loss = 12.4958 (10.529 sec/step)
INFO:tensorflow:global step 3: loss = 11.6073 (8.267 sec/step)
I1022 20:42:47.601801 139794549495680 tf_logging.py:115] global step 3: loss = 11.6073 (8.267 sec/step)
^C
三国纷争
梵蒂冈之花
达令说
相关分类