Uploaded model and main file

.gitignore

@@ -0,0 +1 @@
+*.p

app.py

@@ -0,0 +1,76 @@
+import pickle
+import cv2
+import mediapipe as mp
+import numpy as np
+from PIL import Image
+import requests
+from io import BytesIO
+import gradio as gr
+
+model_dict = pickle.load(open('stacked_model_new.p', 'rb')) 
+
+labels = ['A','B','C','D','E','F','G','H','I','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y']
+
+model = model_dict['model']
+
+
+# get url from backend
+
+def predict(url):
+    response = requests.get(url)
+    print(response)
+    img = Image.open(BytesIO(response.content))
+    img.save('image.jpg')
+    mp_hands = mp.solutions.hands
+    mp_drawing = mp.solutions.drawing_utils
+    mp_drawing_styles = mp.solutions.drawing_styles
+
+    hands = mp_hands.Hands(static_image_mode=False, min_detection_confidence=0.3)
+    hands.maxHands = 1
+
+    data_aux = []
+    x_ = []
+    y_ = []
+
+    frame = cv2.imread('image.jpg')
+
+    H,W, _ = frame.shape
+    frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+    results = hands.process(frame_rgb)
+    if results.multi_hand_landmarks:
+        if(len(results.multi_hand_landmarks) == 1):
+
+            for hand_landmarks in results.multi_hand_landmarks:
+                for i in range(len(hand_landmarks.landmark)):
+                    x = hand_landmarks.landmark[i].x
+                    y = hand_landmarks.landmark[i].y
+
+                    x_.append(x)
+                    y_.append(y)
+
+                for i in range(len(hand_landmarks.landmark)):
+                    x = hand_landmarks.landmark[i].x
+                    y = hand_landmarks.landmark[i].y
+                    data_aux.append(x - min(x_))
+                    data_aux.append(y - min(y_))
+
+            x1 = int(min(x_) * W) - 10
+            y1 = int(min(y_) * H) - 10
+
+            x2 = int(max(x_) * W) - 10
+            y2 = int(max(y_) * H) - 10
+
+            if(len(data_aux) == 42):
+                prediction = model.predict([np.asarray(data_aux)])
+
+                predicted_character = labels[prediction[0]]
+
+                return {"prediction":predicted_character}
+        else:
+
+            return {"prediction": "Too many Hands"}
+
+
+iface = gr.Interface(fn=predict, inputs="image", outputs="text", title="Image to Text Model")
+iface.launch()

requirements.txt

@@ -0,0 +1,42 @@
+absl-py==2.1.0
+attrs==23.2.0
+blinker==1.7.0
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.1
+cycler==0.12.1
+Flask==3.0.3
+flatbuffers==24.3.25
+fonttools==4.51.0
+idna==3.7
+itsdangerous==2.2.0
+jax==0.4.26
+Jinja2==3.1.3
+joblib==1.4.0
+kiwisolver==1.4.5
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mediapipe==0.10.11
+ml-dtypes==0.4.0
+numpy==1.26.4
+opencv-contrib-python==4.9.0.80
+opencv-python==4.9.0.80
+opt-einsum==3.3.0
+packaging==24.0
+pillow==10.3.0
+protobuf==3.20.3
+pycparser==2.22
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+requests==2.31.0
+scikit-learn==1.2.2
+scipy==1.13.0
+six==1.16.0
+sounddevice==0.4.6
+threadpoolctl==3.4.0
+urllib3==2.2.1
+Werkzeug==3.0.2
+xgboost==2.0.3