add description of 19a compat

Author: justinpinkney

README.md

@@ -18,7 +18,7 @@ _Note: This code supports inference using a pretrained model. Training from scra
 ## Installation
 
 - Face Detection and Alignment MTCNN requires the following products:
-  - MATLAB R2019b or later
+  - MATLAB R2019a or later (_now works in R2019a and later!_)
   - Deep Learning Toolbox
   - Computer Vision Toolbox
   - Image Processing Toolbox
@@ -65,10 +65,6 @@ _Face detection from MTCNN in yellow, detections from the built in vision.Cascad
 
 ## Contribute
 
-Please file any bug reports or feature requests as [GitHub issues](https://github.com/matlab-deep-learning/mtcnn-face-detection/issues). In particular comment on the following two issues if they interest you!
-
-- [Support training MTCNN](https://github.com/matlab-deep-learning/mtcnn-face-detection/issues/1)
-- [Support MATLAB versions earlier than R2019b](https://github.com/matlab-deep-learning/mtcnn-face-detection/issues/2)
-
+Please file any bug reports or feature requests as [GitHub issues](https://github.com/matlab-deep-learning/mtcnn-face-detection/issues). In particular if you'd be interested in training your own MTCNN network comment on the following issue: [Support training MTCNN](https://github.com/matlab-deep-learning/mtcnn-face-detection/issues/1)
 
 _Copyright 2019 The MathWorks, Inc._

code/mtcnn/+mtcnn/Detector.m

@@ -25,6 +25,9 @@
         UseGPU = false
         % Use DAG Network for pre 19b compatibility
         UseDagNet = verLessThan('matlab', '9.7')
+    end
+    
+    properties (Access=private)
         % An object providing an inteface to the networks
         Networks
     end

code/mtcnn/+mtcnn/detectFaces.m

@@ -24,6 +24,9 @@
 %                                     (default=[0.5, 0.5, 0.5])
 %            - UseGPU               - Use GPU for processing or not
 %                                     (default=false)
+%            - UseDagNet            - Use DAGNetwork for prediction (for
+%                                     compatibility with R2019a)
+%                                     (default=false R2019b+, =true R2019a)
 % 
 %   Note:
 %       The 5 landmarks detector are in the order: