Updated with architecture

README.md

@@ -32,6 +32,9 @@ It is well-suited for recognizing actions from short trimmed video clips.
 
 - **Base model:** `google/mobilenet_v2_1.0_224`
 - **Architecture:** CNN-GRU
+
+  ![CNN-GRU Architecture](./cnn_architecture.png)
+
 - **Dataset:** UCF101 - Action Recognition Dataset (https://www.kaggle.com/datasets/abdallahwagih/ucf101-videos)
 - **Task:** Video Classification (Action Recognition)
 - **Metrics:** Accuracy