object - 如何在 tensorflow object_detection 中检查训练/评估性能

Question

当我检查张量板以观察训练性能时，只显示了 eval_0(蓝色)结果。



虽然它应该是一个单独的火车(橙色)和 eval(蓝色)结果，如 tensorboard 的网站(https://www.tensorflow.org/guide/summaries_and_tensorboard？)所示。

However, I want to compare the model performance on training dataset and eval dataset.

所以我查了models/research/object_detection/model_main.py，想知道

if I I can get the precision based on the train and eval dataset by set the flag of model_dir to model/eval folder and set the flag of eval_training_data to model/train folder?

flags.DEFINE_string('model_dir', None, 'Path to output model directory '
                     'where event and checkpoint files will be written.')

flags.DEFINE_boolean('eval_training_data', False,
                     'If training data should be evaluated for this job. Note '
                     'that one call only use this in eval-only mode, and '
                     '`checkpoint_dir` must be supplied.')

我对这句话感到困惑。

请注意，一次调用仅在 eval-only 模式下使用它，并且必须提供 checkpoint_dir。

Does it means if I just want run it in eval-only mode, then I must set the checkpoint_dir? And if I want to run it with train and eval at the same time, I don't need to set the checkpoint_dir?

Answer 1

如果您想在验证数据上评估您的模型，您应该使用:

python models/research/object_detection/model_main.py --pipeline_config_path=/path/to/pipeline_file --model_dir=/path/to/output_results --checkpoint_dir=/path/to/directory_holding_checkpoint --run_once=True

如果你想在训练数据上评估你的模型，你应该将 'eval_training_data' 设置为 True，即:

python models/research/object_detection/model_main.py --pipeline_config_path=/path/to/pipeline_file --model_dir=/path/to/output_results --eval_training_data=True --checkpoint_dir=/path/to/directory_holding_checkpoint --run_once=True

我还添加了注释以澄清以前的一些选项:

--pipeline_config_path: 用于训练检测模型的“pipeline.config”文件的路径。此文件应包含要评估的 TFRecords 文件(训练和测试文件)的路径，即:

    ...
    train_input_reader: {
        tf_record_input_reader {
                #path to the training TFRecord
                input_path: "/path/to/train.record"
        }
        #path to the label map 
        label_map_path: "/path/to/label_map.pbtxt"
    }
    ...
    eval_input_reader: {
        tf_record_input_reader {
            #path to the testing TFRecord
            input_path: "/path/to/test.record"
        }
        #path to the label map 
        label_map_path: "/path/to/label_map.pbtxt"
    }
    ...

--model_dir :将写入结果指标的输出目录，特别是可以由张量板读取的“events.*”文件。

--checkpoint_dir : 持有检查点的目录。这是在训练过程中或使用“export_inference_graph.py”导出后写入检查点文件(“model.ckpt.*”)的模型目录。

--run_once : True 只运行一轮评估。