update docs

Summary: Pull Request resolved: facebookresearch#31

Differential Revision: D17895179

Pulled By: ppwwyyxx

fbshipit-source-id: 9aa9d85cfe8e9901aaba5f56cda74224b1e2a51f

Author: ppwwyyxx

projects/DensePose/README.md

@@ -25,15 +25,15 @@ python /path/to/detectron2/projects/DensePose/train_net.py --config-file <config
 For example, to launch end-to-end DensePose-RCNN training with ResNet-50 FPN backbone on a single GPU,
 one should execute:
 ```bash
-python /path/to/detectron2/projects/DensePose/train_net.py --config-file /path/to/detectron2/projects/DensePose/configs/densepose_R_50_FPN_s1x.yaml
+python /path/to/detectron2/projects/DensePose/train_net.py --config-file configs/densepose_R_50_FPN_s1x.yaml
 ```
 
-## Testing
+## Evaluation
 
-Model testing can be done in the same way as training, except for an additional flag `--eval-only` and
-model location specification through `MODEL.WEIGHT model.pth` in the command line
+Model evaluation can be done in the same way as training, except for an additional flag `--eval-only` and
+model location specification through `MODEL.WEIGHTS model.pth` in the command line
 ```bash
-python /path/to/detectron2/projects/DensePose/train_net.py --config-file /path/to/detectron2/projects/DensePose/configs/densepose_R_50_FPN_s1x.yaml --eval-only MODEL.WEIGHT model.pth
+python /path/to/detectron2/projects/DensePose/train_net.py --config-file configs/densepose_R_50_FPN_s1x.yaml --eval-only MODEL.WEIGHTS model.pth
 ```
 
 ## Tools
@@ -44,10 +44,10 @@ We provide tools which allow one to:
  - visualize DensePose model results;
 
 `query_db` is a tool to print or visualize DensePose data in a dataset.
-Details on this tool can be found in [`TOOL_QUERY_DB.md`](doc/TOOL_QUERY_DB.md) 
+Details on this tool can be found in [`TOOL_QUERY_DB.md`](doc/TOOL_QUERY_DB.md)
 
 `apply_net` is a tool to print or visualize DensePose results.
-Details on this tool can be found in [`TOOL_APPLY_NET.md`](doc/TOOL_APPLY_NET.md) 
+Details on this tool can be found in [`TOOL_APPLY_NET.md`](doc/TOOL_APPLY_NET.md)
 
 ## <a name="CitingDensePose"></a>Citing DensePose
 

projects/DensePose/doc/TOOL_APPLY_NET.md

@@ -14,7 +14,7 @@ python apply_net.py dump [-h] [-v] [--output <dump_file>] <config> <model> <inpu
 
 There are three mandatory arguments:
  - `<config>`, configuration file for a given model;
- - `<model>`, model file with trained parameters 
+ - `<model>`, model file with trained parameters
  - `<input>`, input image file name, pattern or folder
 
 One can additionally provide `--output` argument to define the output file name,
@@ -45,7 +45,7 @@ python apply_net.py show [-h] [-v] [--min_score <score>] [--nms_thresh <threshol
 
 There are four mandatory arguments:
  - `<config>`, configuration file for a given model;
- - `<model>`, model file with trained parameters 
+ - `<model>`, model file with trained parameters
  - `<input>`, input image file name, pattern or folder
  - `<visualizations>`, visualizations specifier; currently available visualizations are:
    * `bbox` - bounding boxes of detected persons;
@@ -72,22 +72,22 @@ with ResNet-50 FPN backbone using different visualizations for image `image.jpg`
 ```bash
 python apply_net.py show configs/densepose_R_50_FPN_s1x.yaml DensePose_ResNet50_FPN_s1x-e2e.pkl image.jpg bbox,dp_segm -v
 ```
-![Bounding Box + Segmentation Visualization](images/res_bbox_dp_segm.png)
+![Bounding Box + Segmentation Visualization](images/res_bbox_dp_segm.jpg)
 
 2. Show bounding box and estimated U coordinates for body parts:
 ```bash
 python apply_net.py show configs/densepose_R_50_FPN_s1x.yaml DensePose_ResNet50_FPN_s1x-e2e.pkl image.jpg bbox,dp_u -v
 ```
-![Bounding Box + U Coordinate Visualization](images/res_bbox_dp_u.png)
+![Bounding Box + U Coordinate Visualization](images/res_bbox_dp_u.jpg)
 
 3. Show bounding box and estimated V coordinates for body parts:
 ```bash
 python apply_net.py show configs/densepose_R_50_FPN_s1x.yaml DensePose_ResNet50_FPN_s1x-e2e.pkl image.jpg bbox,dp_v -v
 ```
-![Bounding Box + V Coordinate Visualization](images/res_bbox_dp_v.png)
+![Bounding Box + V Coordinate Visualization](images/res_bbox_dp_v.jpg)
 
 4. Show bounding box and estimated U and V coordinates via contour plots:
 ```bash
 python apply_net.py show configs/densepose_R_50_FPN_s1x.yaml DensePose_ResNet50_FPN_s1x-e2e.pkl image.jpg dp_contour,bbox -v
 ```
-![Bounding Box + Contour Visualization](images/res_bbox_dp_contour.png)
+![Bounding Box + Contour Visualization](images/res_bbox_dp_contour.jpg)

projects/TridentNet/README.md

@@ -23,15 +23,14 @@ python /path/to/detectron2/projects/TridentNet/train_net.py --config-file <confi
 For example, to launch end-to-end TridentNet training with ResNet-50 backbone on 8 GPUs,
 one should execute:
 ```bash
-python /path/to/detectron2/projects/TridentNet/train_net.py --config-file /path/to/detectron2/projects/TridentNet/configs/tridentnet_fast_R_50_C4_1x.yaml --num_gpus 8
+python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --num_gpus 8
 ```
 
-## Testing
+## Evaluation
 
-Model testing can be done in the same way as training, except for an additional flag `--eval-only` and
-model location specification through `MODEL.WEIGHT model.pth` in the command line
+Model evaluationcan be done similarly:
 ```bash
-python /path/to/detectron2/projects/TridentNet/train_net.py --config-file /path/to/detectron2/projects/TridentNet/configs/tridentnet_fast_R_50_C4_1x.yaml --eval-only MODEL.WEIGHT model.pth
+python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --eval-only MODEL.WEIGHTS model.pth
 ```
 
 ## Results on MS-COCO in Detectron2