From 2e3f90cb39b99007783a46bb96dc419198bcc4c8 Mon Sep 17 00:00:00 2001 From: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com> Date: Thu, 13 Aug 2020 19:26:11 +0800 Subject: [PATCH] Update docs (#3549) * Update usage and trouble shooting links * update support for pt1.6 --- README.md | 4 +++- docs/getting_started.md | 7 ++++--- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index ad0cd380881..c48f8616532 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ Documentation: https://mmdetection.readthedocs.io/ MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the OpenMMLab project developed by [Multimedia Laboratory, CUHK](http://mmlab.ie.cuhk.edu.hk/). -The master branch works with **PyTorch 1.3 to 1.5**. +The master branch works with **PyTorch 1.3 to 1.6**. The old v1.x branch works with PyTorch 1.1 to 1.4, but v2.0 is strongly recommended for faster speed, higher performance, better design and more friendly usage. ![demo image](resources/coco_test_12510.jpg) @@ -111,6 +111,8 @@ Please see [getting_started.md](docs/getting_started.md) for the basic usage of We provide [colab tutorial](demo/MMDet_Tutorial.ipynb) for beginners. There are also tutorials for [finetuning models](docs/tutorials/finetune.md), [adding new dataset](docs/tutorials/new_dataset.md), [designing data pipeline](docs/tutorials/data_pipeline.md), and [adding new modules](docs/tutorials/new_modules.md). +For trouble shooting, please refer to [trouble_shooting.md](docs/trouble_shooting.md) + ## Contributing We appreciate all contributions to improve MMDetection. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guideline. diff --git a/docs/getting_started.md b/docs/getting_started.md index 64e431c37e4..e8c03a145ee 100644 --- a/docs/getting_started.md +++ b/docs/getting_started.md @@ -280,9 +280,10 @@ Optional arguments are: - `--resume-from ${CHECKPOINT_FILE}`: Resume from a previous checkpoint file. - `--options 'Key=value'`: Overide some settings in the used config. -Difference between `resume-from` and `load-from`: -`resume-from` loads both the model weights and optimizer status, and the epoch is also inherited from the specified checkpoint. It is usually used for resuming the training process that is interrupted accidentally. -`load-from` only loads the model weights and the training epoch starts from 0. It is usually used for finetuning. +**Note**: + +- `resume-from` loads both the model weights and optimizer status, and the epoch is also inherited from the specified checkpoint. It is usually used for resuming the training process that is interrupted accidentally. +- For more clear usage, the original `load-from` is deprecated and you can use `--options 'load_from="path/to/you/model"'` instead. It only loads the model weights and the training epoch starts from 0 which is usually used for finetuning. ### Train with multiple machines