我尝试实现Tensorflow对象检测API，并且在培训期间，我的结果低于预期，而且运行时间很长，而且没有得到更多结果。
我在测试集中只使用了7张图像和3张图像，仍然没有得到更多结果
我正在使用Tensorflow1.15
INFO:tensorflow:Done calling model_fn.
I1207 15:04:32.265669 9380 estimator.py:1150] Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
I1207 15:04:32.267668 9380 basic_session_run_hooks.py:541] Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
I1207 15:04:37.474951 9380 monitored_session.py:240] Graph was finalized.
2019-12-07 15:04:37.478682: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2019-12-07 15:04:37.494165: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2019-12-07 15:04:37.832387: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce 830M major: 5 minor: 0 memoryClockRate(GHz): 1.15
pciBusID: 0000:0a:00.0
2019-12-07 15:04:37.841191: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2019-12-07 15:04:37.853644: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2019-12-07 15:04:37.865194: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll
2019-12-07 15:04:37.875714: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll
2019-12-07 15:04:37.889732: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll
2019-12-07 15:04:37.905515: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll
2019-12-07 15:04:37.924530: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-07 15:04:37.932013: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2019-12-07 15:04:39.474886: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-07 15:04:39.480670: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2019-12-07 15:04:39.488584: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2019-12-07 15:04:39.493975: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1389 MB memory) -> physical GPU (device: 0, name: GeForce 830M, pci bus id: 0000:0a:00.0, compute capability: 5.0)
INFO:tensorflow:Restoring parameters from training/model.ckpt-0
I1207 15:04:39.522326 9380 saver.py:1284] Restoring parameters from training/model.ckpt-0
WARNING:tensorflow:From C:\Users\milan\Downloads\models-master\TFO\lib\site-packages\tensorflow_core\python\training\saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
W1207 15:04:42.039816 9380 deprecation.py:323] From C:\Users\milan\Downloads\models-master\TFO\lib\site-packages\tensorflow_core\python\training\saver.py:1069: get_checkpoint_mtimes (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file utilities to get mtimes.
INFO:tensorflow:Running local_init_op.
I1207 15:04:43.612918 9380 session_manager.py:500] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I1207 15:04:44.214592 9380 session_manager.py:502] Done running local_init_op.
INFO:tensorflow:Saving checkpoints for 0 into training/model.ckpt.
I1207 15:04:57.934353 9380 basic_session_run_hooks.py:606] Saving checkpoints for 0 into training/model.ckpt.
2019-12-07 15:05:11.850788: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-07 15:05:12.891584: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows
Relying on driver to perform ptx compilation. This message will be only logged once.
2019-12-07 15:05:13.030221: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
INFO:tensorflow:loss = 10.3425045, step = 0
I1207 15:05:22.538612 9380 basic_session_run_hooks.py:262] loss = 10.3425045, step = 0