update README.md

README.md

@@ -7,46 +7,39 @@
 <div align="center">
     <p>
         <a align="center" href="https://github.com/saaresearch/ODRS" target="_blank">
-            <img width="70%" src="docs/img/logo.png">
+            <img width="50%" src="docs/img/logo.png">
         </a>
     </p>
     <div style='display: block;'>
         <a href="https://itmo.ru/">
             <img width="10%" src="docs/img/itmo.png" alt="Acknowledgement to ITMO">
         </a>
-        <a href="">
+        <a href="https://colab.research.google.com/drive/1iTx37IwvGyms82626ALYqZfdEbhGmJll?usp=sharing">
             <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab">
         </a>
     </div>
 </div>
+<br></br>
 ODRS - it an open source recommendation system for training object detection models. Our system allows you to choose the most 
 profitable existing object recognition models based on user preferences and data. In addition to choosing the 
 architecture of the model, the system will help you start training and configure the environment.
 
+<img src="docs/img/prew.gif" width="1280" height="720">
+
+<br></br>
 The proposed recommendation system consists of several components that interact to generate recommendations for machine learning pipelines.
 <div align="center">
-    <img src="docs/img/system.jpg" width="400">
+    <img src="docs/img/alg.gif" width="1280" height="720">
 </div>
 External parameters (received from users and third-party resources):
 * Dataset: Represents input data (video frames) and associated metadata (e.g. image size, quality, number of objects).
 * Model: Framework provides an opportunity to train the most popular object recognition models (including setting up the environment 
 and choosing the architecture of a specific model). Considered two-stage detectors models such as Faster R-CNN and Mask R-CNN as 
 well as one-stage detectors such as SSD and YOLO (including families v5, v7, v8).
-<br/>
-<br>
-<div align="center">
-    <img src="docs/img/model.png" width="400">
-</div>
-
 Internal components:
 
-* ***RecommendationEngine***: generates recommendations based on user data and dataset characteristics.
-<br/>
-<br>
-<div align="center">
-    <img src="docs/img/rec_alg.jpg" width="400">
-</div>
-
+***RecommendationEngine***: 
+generates recommendations based on user data and dataset characteristics.
 The recommendation algorithm is based on production rules. The primary set of rules (knowledge base) is formed on 
 the basis of the results of the analysis of scientific sources and standard data sets, but also empirical processing 
 of data sets from specific industries.
@@ -57,16 +50,9 @@ The main criteria for drawing up the rules were chosen:
 3. The speed of the model on GPU and CPU
 4. Supported image format and dimension
 
+***Training*** - Training of models proposed by the system
 
-* ***Training*** - Training of models proposed by the system
-<br/>
-<br>
-<div align="center">
-    <img src="docs/img/train.jpg" width="400">
-</div>
-
-* ***Evaluation*** – evaluation of the quality of training models
-
+***Evaluation*** – evaluation of the quality of training models
 
 ## Contents