[英]Tensorflow 2 Object Detection API - Official Models: What is VAL_JSON_FILE?
To use any of the Object Detection models from TensorFlow's Official Models in the ModelZoo, there is a variable called "VAL_JSON_FILE", which is used for the params_override
argument.要使用 ModelZoo 中 TensorFlow 官方模型中的任何 Object 检测模型,有一个名为“VAL_JSON_FILE”的变量,用于
params_override
参数。 For my use case, I am performing transfer learning on RetinaNet.对于我的用例,我在 RetinaNet 上执行迁移学习。 The command and arguments are found below:
命令和 arguments 如下所示:
TPU_NAME="<your GCP TPU name>"
MODEL_DIR="<path to the directory to store model files>"
RESNET_CHECKPOINT="<path to the pre-trained Resnet-50 checkpoint>"
TRAIN_FILE_PATTERN="<path to the TFRecord training data>"
EVAL_FILE_PATTERN="<path to the TFRecord validation data>"
VAL_JSON_FILE="<path to the validation annotation JSON file>"
python3 ~/models/official/vision/detection/main.py \
--strategy_type=tpu \
--tpu="${TPU_NAME?}" \
--model_dir="${MODEL_DIR?}" \
--mode=train \
--params_override="{ type: retinanet, train: { checkpoint: { path: ${RESNET_CHECKPOINT?}, prefix: resnet50/ }, train_file_pattern: ${TRAIN_FILE_PATTERN?} }, eval: { val_json_file: ${VAL_JSON_FILE?}, eval_file_pattern: ${EVAL_FILE_PATTERN?} } }"
This is the link: https://github.com/tensorflow/models/blob/master/official/vision/detection/README.md这是链接: https://github.com/tensorflow/models/blob/master/official/vision/detection/README.md
What is VAL_JSON_FILE used for? VAL_JSON_FILE 是做什么用的? Is it necessary?
有必要吗? How can I find/create the file?
如何找到/创建文件?
Thanks!谢谢!
https://gregsdennis.github.io/Manatee.Json/usage/schema/validation.html https://gregsdennis.github.io/Manatee.Json/usage/schema/validation.html
This link is somewhat relevant and can provide you with more info on JSON validation.此链接有些相关,可以为您提供有关 JSON 验证的更多信息。 It seems to me like it's a testing (validation) of the JSON objects;
在我看来,这是对 JSON 对象的测试(验证); checking whether it matches types.
检查它是否匹配类型。
Have you tried to run the learning without that file?您是否尝试过在没有该文件的情况下运行学习? I'm not certain but it could be an optional file, or there is a default one already without necessary changes needed.
我不确定,但它可能是一个可选文件,或者已经有一个默认文件,无需进行必要的更改。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.