update readme with pifpaf models

README.md

@@ -52,9 +52,13 @@ mkdir arrays models kitti nuscenes logs
 
 ### Pre-trained Models
 * Download a MonoLoco pre-trained model from 
-[Google Drive](https://drive.google.com/open?id=1F7UG1HPXGlDD_qL-AN5cv2Eg-mhdQkwv) and save it in `data/models`
+[Google Drive](https://drive.google.com/open?id=1F7UG1HPXGlDD_qL-AN5cv2Eg-mhdQkwv) and save it in `data/models` 
-* Download a Pifpaf pre-trained model from [openpifpaf](https://github.com/vita-epfl/openpifpaf) project 
+(default) or in any folder and call it through the command line option `--model <model path>`
-and save it into `data/models`
+* Pifpaf pre-trained model will be automatically downloaded at the first run. 
+Three standard, pretrained models are available when using the command line option 
+`--checkpoint resnet50`, `--checkpoint resnet101` and `--checkpoint resnet152`.
+Alternatively, you can download a Pifpaf pre-trained model from [openpifpaf](https://github.com/vita-epfl/openpifpaf)
+ and call it with `--checkpoint  <pifpaf model path>`
 
 
 # Interfaces
@@ -114,14 +118,14 @@ Below an example on a generic image from the web, created with:
 # Webcam
 <img src="docs/webcam_short.gif" height=350 alt="example image" />
 
-MonoLoco can run on personal computers with no GPU and low resolution images (e.g. 256x144).
+MonoLoco can run on personal computers with only CPU and low resolution images (e.g. 256x144) at ~2fps.
 
 It support 3 types of visualizations: `front`, `bird` and `combined`
 Multiple visualizations can be combined in different windows.
 
 The above gif has been obtained running on a Macbook the command:
 
-`python src/main.py predict --webcam --scale 0.2 --output_types combined --z_max 10`
+`python src/main.py predict --webcam --scale 0.2 --output_types combined --z_max 10 --checkpoint resnet50`
 
 # Preprocess
 

src/main.py

@@ -39,7 +39,7 @@ def cli():
                              default='data/nuscenes/')
 
     # Predict (2D pose and/or 3D location from images)
-    # 0) General arguments
+    # General
     predict_parser.add_argument('--networks', nargs='+', help='Run pifpaf and/or monoloco', default=['monoloco'])
     predict_parser.add_argument('images', nargs='*', help='input images')
     predict_parser.add_argument('--glob', help='glob expression for input images (for many images)')
@@ -49,13 +49,12 @@ def cli():
                                      'json bird front combined for Monoloco')
     predict_parser.add_argument('--show', help='to show images', action='store_true')
 
-    # 1)Pifpaf arguments
+    # Pifpaf
     nets.cli(predict_parser)
     decoder.cli(predict_parser, force_complete_pose=True, instance_threshold=0.1)
-    predict_parser.add_argument('--checkpoint', help='pifpaf model to load')
     predict_parser.add_argument('--scale', default=1.0, type=float, help='change the scale of the image to preprocess')
 
-    # 2) Monoloco argument
+    # Monoloco
     predict_parser.add_argument('--model', help='path of MonoLoco model to load',
                                 default="data/models/monoloco-190513-1437.pkl")
     predict_parser.add_argument('--hidden_size', type=int, help='Number of hidden units in the model', default=256)

src/predict/pifpaf.py

@@ -47,12 +47,6 @@ def factory_from_args(args):
     # Merge the model_pifpaf argument
     if not args.checkpoint:
         args.checkpoint = 'resnet152'  # Default model Resnet 152
-    elif args.checkpoint == 'resnet50':
-        args.checkpoint = 'data/models/resnet50block5-pif-paf-edge401-190424-122009-f26a1f53.pkl'
-    elif args.checkpoint == 'resnet101':
-        args.checkpoint = 'data/models/resnet101block5-pif-paf-edge401-190412-151013-513a2d2d.pkl'
-    elif args.checkpoint == 'resnet152':
-        args.checkpoint = 'data/models/resnet152block5-pif-paf-edge401-190412-121848-8d771fcc.pkl'
     # glob
     if not args.webcam:
         if args.glob: