Docs updated

app.py

@@ -0,0 +1,61 @@
+import cv2
+import numpy as np
+import gradio as gr
+from tensorflow.keras.models import load_model
+
+# Define constants
+SEQUENCE_LENGTH = 20  # Number of frames to extract
+IMAGE_HEIGHT = 64  # Height of each frame
+IMAGE_WIDTH = 64  # Width of each frame
+CLASSES_LIST = ["Archery", "BabyCrawling", "Balance_Beam", "EyeMakeup", "LipStick"]
+
+# Load the model
+loaded_model = load_model(r"LRCN_model.h5")
+
+def frames_extraction(video_reader):
+    frames_list = []
+    video_frames_count = int(video_reader.get(cv2.CAP_PROP_FRAME_COUNT))
+    skip_frames_window = max(int(video_frames_count / SEQUENCE_LENGTH), 1)  # default skip is 1
+    for frame_counter in range(SEQUENCE_LENGTH):
+        video_reader.set(cv2.CAP_PROP_POS_FRAMES, frame_counter * skip_frames_window)
+        success, frame = video_reader.read()
+        if not success:
+            break
+
+        resized_frame = cv2.resize(frame, (IMAGE_HEIGHT, IMAGE_WIDTH))
+        normalized_frame = resized_frame / 255  # color 0-255
+        frames_list.append(normalized_frame)
+    video_reader.release()
+
+    return frames_list
+
+# Function to classify the video
+def classify_video(frames):
+    predicted_labels = np.argmax(loaded_model.predict(frames), axis=1)
+    predicted_class_label = CLASSES_LIST[predicted_labels[0]]  # Ensure we get the label for the first prediction
+    return predicted_class_label
+
+# Define the prediction function
+def predict_video(video_file):
+    video_capture = cv2.VideoCapture(video_file)
+    features = []
+    video_reader = video_capture
+    frames = frames_extraction(video_reader)
+    if len(frames) == SEQUENCE_LENGTH:
+        features.append(frames)
+        features = np.asarray(features)
+        predicted_class = classify_video(features)
+        video_capture.release()
+        return predicted_class
+
+# Gradio interface definition
+iface = gr.Interface(
+  fn=predict_video,
+  inputs=gr.Video(),
+  outputs="text",
+  title="Action Recognition with LSTM",
+  description="Upload a video and get the predicted action class."
+)
+
+# Launch the Gradio interface
+iface.launch()

requirements.txt

@@ -0,0 +1,9 @@
+os-sys
+opencv-python-headless
+pafy
+numpy
+datetime
+tensorflow
+moviepy
+matplotlib
+scikit-learn