Features added

README.md

@@ -2,7 +2,7 @@
 
 ![alt text](https://raw.githubusercontent.com/virajmavani/semi-auto-image-annotation-tool/master/demo.gif)
 
-Semi Automatic Image Annotation Toolbox with RetinaNet as the suggesting algorithm. The toolbox suggests 80 class objects from the MS COCO dataset using a pretrained RetinaNet model.
+Semi Automatic Image Annotation Toolbox with tensorflow and keras object detection models.
 
 ## Installation
 
@@ -14,7 +14,13 @@ Semi Automatic Image Annotation Toolbox with RetinaNet as the suggesting algorit
    Please make sure `tensorflow` is installed as per your systems requirements.
    Also, make sure Keras 2.1.3 or higher and OpenCV 3.x is installed.
 
-3) Download the [pretrained weights](https://github.com/fizyr/keras-retinanet/releases/download/0.3.1/resnet50_coco_best_v2.1.0.h5) and save it in /snapshots.
+3) a) For Keras model - Download the [pretrained weights](https://github.com/fizyr/keras-retinanet/releases/download/0.3.1/resnet50_coco_best_v2.1.0.h5) and save it in /snapshots/keras.
+
+   b) For tensorflow model get the desired model from [here](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) and extract it in /sanpshots/tensorfow
+
+   c) You can even save custom pre trained model in the respective directory.
+
+
 
 ### Dependencies
 
@@ -28,19 +34,30 @@ For, Python >= 3.5
 
 ### Instructions
 
-1) Select the COCO object classes for which you need suggestions from the drop-down menu and add them.
+1) Select the COCO object classes for which you need suggestions from the drop-down menu and add them. Or simply click on ```Add all classes``` .
+
+2) Select the desired model and click on ```Add model```.
+
+3) Click on ```detect``` button.
 
-2) When annotating manually, select the object class from the List and while keep it selected, select the BBox.
+4) When annotating manually, select the object class from the List and while keep it selected, select the BBox.
 
-3) The final annotations can be found in the file `annotations.csv` in ./annotations/
+5) The final annotations can be found in the file `annotations.csv` in ./annotations/ . Also a xml file will saved.
 
 ### Usage
+
+For MSCOCO dataset
 ```
 python main.py
 ```
+For any other dataset-
 
-Tested on:
+First change the labels in config.py (for keras model) or in tf_config.py( for tensorflow model).
+Then run:
+```python main.py
+```
 
+#### Tested on:
 1. Windows 10
 
 2. Linux 16.04