如何在张量流object_detection中检查训练/评估性能 [英] how to check both training/eval performances in tensorflow object_detection

问题描述

当我检查张量板以观察训练效果时，仅显示eval_0（蓝色）结果。

When I check the tensorboard for observing the training performance, there only shows the eval_0 (in blue) result.

虽然它应该是一列单独的火车（在橙色和eval（蓝色）结果显示在tensorboard网站上（ https：//www.tensorflow。 org / guide / summaries_and_tensorboard ？）。

While it should be a separate train (in orange) and eval (in blue) result as shown in the website of tensorboard (https://www.tensorflow.org/guide/summaries_and_tensorboard?).

不过，我想比较训练数据集
的模型性能和评估数据集。

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

所以我检查了models / research / object_detection / model_main.py并想知道

So I checked the models/research/object_detection/model_main.py and want to know

如果II可以通过
根据火车和评估数据集获得精度，请将 model_dir 的标志设置为 model / eval 文件夹并将 eval_training_data 的
标志设置为 model / train 文件夹？

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。

And I'm confused with this sentence.

请注意，一个呼叫仅在仅评估模式下使用，并且必须提供checkpoint_dir。

这是否意味着如果我只想在仅eval模式下运行它，那么我必须将
设置为checkpoint_dir吗？而且，如果我想同时在
中使用train和eval来运行它，我不需要设置checkpoint_dir吗？

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?

推荐答案

如果要根据验证数据评估模型，则应使用：

If you want to evaluate your model on validation data you should use:

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

如果要根据训练数据评估模型，则应将 eval_training_data设置为True，即：

If you want to evaluate your model on training data, you should set 'eval_training_data' as True, that is:

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

---

我还添加了注释以阐明某些先前的选择：

---

I also add comments to clarify some of previous options:

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

--pipeline_config_path: path to "pipeline.config" file used to train detection model. This file should include paths to the TFRecords files (train and test files) that you want to evaluate, i.e. :

    ...
    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 ：将在其中写入结果度量的输出目录，尤其是可由tensorboard读取的事件。*文件。

--model_dir: Output directory where resulting metrics will be written, particularly "events.*" files that can be read by tensorboard.

-checkpoint_dir ：Directo瑞恩拿着一个检查站。在训练过程中，或使用 export_inference_graph.py导出检查点文件后，即在其中写入检查点文件（ model.ckpt。*）的模型目录。

--checkpoint_dir: Directory holding a checkpoint. That is the model directory where checkpoint files ("model.ckpt.*") has been written, either during training process, or after export it by using "export_inference_graph.py".

-run_once ：仅运行一次评估即可。

--run_once: True to run just one round of evaluation.

这篇关于如何在张量流object_detection中检查训练/评估性能的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！