update docs

Summary: Pull Request resolved: fairinternal/detectron2#331

Differential Revision: D18572260

Pulled By: ppwwyyxx

fbshipit-source-id: 39d340f726912255b186c3f0f20f939ff02a2cc0

Author: ppwwyyxx

GETTING_STARTED.md

@@ -33,7 +33,7 @@ For details of the command line arguments, see `demo.py -h`. Some common ones ar
 * To save outputs to a directory (for images) or a file (for webcam or video), use `--output`.
 
 
-### Train a Standard Model
+### Use Detectron2 in Command Line
 
 We provide a script in "tools/train_net.py", that is made to train
 all the configs provided in detectron2.
@@ -48,7 +48,7 @@ python tools/train_net.py --num-gpus 8 \
 	--config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
 ```
 
-The configs are made for 8-GPU training. To train on 1 GPU, use:
+The configs are made for 8-GPU training. To train on 1 GPU, change the batch size with:
 ```
 python tools/train_net.py \
 	--config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \

INSTALL.md

@@ -6,6 +6,7 @@ The [Dockerfile](https://github.com/facebookresearch/detectron2/blob/master/Dock
 also installs detectron2 with a few simple commands.
 
 ### Requirements
+- Linux or macOS
 - Python >= 3.6
 - PyTorch 1.3
 - [torchvision](https://github.com/pytorch/vision/) that matches the PyTorch installation.
@@ -16,7 +17,7 @@ also installs detectron2 with a few simple commands.
 - GCC >= 4.9
 
 
-### Build detectron2
+### Build Detectron2
 
 After having the above dependencies, run:
 ```

detectron2/data/datasets/register_coco.py

@@ -67,7 +67,7 @@ def register_coco_panoptic_separated(
     Args:
         name (str): the name that identifies a dataset,
             e.g. "coco_2017_train_panoptic"
-        metadata (str): extra metadata associated with this dataset.
+        metadata (dict): extra metadata associated with this dataset.
         image_root (str): directory which contains all the images
         panoptic_root (str): directory which contains panoptic annotation images
         panoptic_json (str): path to the json panoptic annotation file

docs/tutorials/datasets.md

@@ -48,7 +48,7 @@ will load the image from "file_name" and load "sem_seg" from "sem_seg_file_name"
 + `sem_seg`: semantic segmentation ground truth in a 2D `torch.Tensor`. Values in the array represent
    category labels.
 + `height`, `width`: integer. The shape of image.
-+ `image_id` (str): a string to identify this image. Mainly used by certain datasets
++ `image_id` (str): a string to identify this image. Used
 	during evaluation to identify the image, but a dataset may use it for different purposes.
 + `annotations` (list[dict]): the per-instance annotations of every
   instance in this image. Each annotation dict may contain: