Update app.py

app.py

@@ -43,13 +43,13 @@ import gradio as gr
 # In[46]:
 
 
-labels = {0: 'Normal', 1: 'RoadAccidents', 2: 'Violent'}
+labels = {0: 'Voilent', 1: 'Normal', 2: 'RoadAccidents'}
 
 
 # In[47]:
 
 
-model = keras.models.load_model("Frame16_EffiecientNet_Model5.h5", compile=False)
+model = keras.models.load_model("Frame16_Densenet_Model.h5", compile=False)
 
 
 # In[48]:
@@ -58,19 +58,7 @@ model = keras.models.load_model("Frame16_EffiecientNet_Model5.h5", compile=False
 def videoToFrames(video):
 
     # Read the video from specified path 
-    cam = cv2.VideoCapture(video) 
-
-    '''
-    try: 
-        
-        # creating a folder named data 
-        if not os.path.exists('/home/shubham/__New-D__/VITA/Project/redundant/data/Abuse'): 
-            os.makedirs('/home/shubham/__New-D__/VITA/Project/redundant/data/Abuse') 
-
-    # if not created then raise error 
-    except OSError: 
-        print ('Error: Creating directory of data') 
-    '''
+    cam = cv2.VideoCapture(video)
     
     # frame 
     currentframe = 1
@@ -80,17 +68,7 @@ def videoToFrames(video):
         ret,frame = cam.read() 
         
 
-        if ret: 
-            # if video is still left continue creating images 
-            # name = '/home/shubham/__New-D__/VITA/Project/redundant/data/Abuse/frame' + str(currentframe) + '.jpg'
-            # print ('Creating...' + name) 
-
-            # writing the extracted images 
-            
-            # cv2.imwrite(name, frame) 
-
-            # increasing counter so that it will 
-            # show how many frames are created 
+        if ret:  
             currentframe += 1
         else: 
             break
@@ -125,16 +103,7 @@ def hconcat_resize(img_list, interpolation=cv2.INTER_CUBIC):
 
 def make_average_predictions(video_file_path, predictions_frames_count):
     
-    confidences = {}
-    
     number_of_classes = 3
-     
-    # Initializing the Numpy array which will store Prediction Probabilities
-    
-    #predicted_labels_probabilities_np = np.zeros((predictions_frames_count, number_of_classes), dtype = np.float)
-
-    
-    # Reading the Video File using the VideoCapture Object
     
     video_reader = cv2.VideoCapture(video_file_path)
     
@@ -263,6 +232,8 @@ def make_average_predictions(video_file_path, predictions_frames_count):
                 print(predicted_labels_probabilities)
 
                 #predicted_labels_probabilities_np[frame_counter] = predicted_labels_probabilities
+                
+                #Argmax is most commonly used in machine learning for finding the class with the largest predicted probability.
 
                 prediction = np.argmax(predicted_labels_probabilities)
 
@@ -288,51 +259,8 @@ def make_average_predictions(video_file_path, predictions_frames_count):
                     break
         except:
             break
-
-    """# Calculating Average of Predicted Labels Probabilities Column Wise
-
-    predicted_labels_probabilities_averaged = predicted_labels_probabilities_np.mean(axis = 0)
-
- 
-
-    # Sorting the Averaged Predicted Labels Probabilities
-
-    predicted_labels_probabilities_averaged_sorted_indexes = np.argsort(predicted_labels_probabilities_averaged)[::-1]
-
-    predicted_labels_probabilities_averaged_sorted_indexes = predicted_labels_probabilities_averaged_sorted_indexes[:3]
-
     
-    
-    # Iterating Over All Averaged Predicted Label Probabilities
-
-    for predicted_label in predicted_labels_probabilities_averaged_sorted_indexes:
-
- 
-
-        # Accessing The Class Name using predicted label.
-
-        predicted_class_name = labels[predicted_label]
-
- 
-
-        # Accessing The Averaged Probability using predicted label.
-
-        predicted_probability = predicted_labels_probabilities_averaged[predicted_label]
-
- 
-
-        print(f"CLASS NAME: {predicted_class_name}   AVERAGED PROBABILITY: {(predicted_probability*100):.2}")
-        
-        confidences[predicted_class_name]=predicted_probability 
-        
-        
-     
-
-    # Closing the VideoCapture Object and releasing all resources held by it.
-
-    video_reader.release()"""
-    
-    return confidences, features
+    return features
 
 
 # In[56]:
@@ -351,38 +279,31 @@ def most_frequent(List):
     return num
 
 
-# In[64]:
-
-
-video = "/home/shubham/__New-D__/VITA/Project/redundant/production ID_4959443.mp4"
-#labels = {0: 'RoadAccidents', 1: 'Normal', 2: 'Violent'}
-framecount = videoToFrames(video)
-confidences, features = make_average_predictions(video, framecount)
-List = most_frequent(features)
-print("The Video You Have Entered is of",labels.get(List))
 
-#print(confidences)    
+description = """
+Detecting abnormal events automatically from surveillance if any anomalous event happens in front of the surveillance cameras, it can be detected immediately by designing a model.
+"""
 
+def classify_video(video):
 
-# In[53]:
-
-
-"""def classify_video(video):
-
-    labels = {0: 'RoadAccidents', 1: 'Normal', 2: 'Violent'}
+    labels = {0: 'Voilent', 1: 'Normal', 2: 'RoadAccidents'}
     framecount = videoToFrames(video)
-    confidences, features = make_average_predictions(video, framecount)
+    features = make_average_predictions(video, framecount)
     List = most_frequent(features)
     #print("The Video You Have Entered is of",labels.get(List))
     return labels.get(List)
-
+example=[["Example_1.mp4"],["Example_2.mp4"],["Example_3.mp4"]]
 demo = gr.Interface(classify_video, 
                     inputs=gr.Video(), 
-                    outputs=gr.outputs.Label(),  
+                    outputs=gr.outputs.Label(),
+                    title="Anomaly Detection in Surveillance Videos",
+                    description=description,
+                    theme="peach",
+                    examples=example,  
                     cache_examples=True)
 
 if __name__ == "__main__":
-    demo.launch(share=False)"""
+    demo.launch(share=False)
 
 
 # In[ ]:
@@ -395,4 +316,3 @@ if __name__ == "__main__":
 
 
 
-