Spaces:
Build error
Build error
| import pickle | |
| import cv2 | |
| import mediapipe as mp | |
| import numpy as np | |
| import tensorflow as tf | |
| from collections import deque | |
| import gradio as gr | |
| # Constants (fallback defaults) | |
| SEQUENCE_LENGTH = 30 | |
| FEATURE_LENGTH = 168 | |
| # Load model & preprocessing | |
| def load_model_and_preprocessing(): | |
| global scaler, label_encoder, model, labels_dict | |
| with open('lstm_preprocessing.pickle', 'rb') as f: | |
| preproc = pickle.load(f) | |
| scaler = preproc['scaler'] | |
| label_encoder = preproc['label_encoder'] | |
| timesteps = preproc['timesteps'] | |
| n_features = preproc['n_features'] | |
| global SEQUENCE_LENGTH, FEATURE_LENGTH | |
| SEQUENCE_LENGTH = timesteps | |
| FEATURE_LENGTH = n_features | |
| model = tf.keras.models.load_model('lstm_model.h5') | |
| labels_dict = {0:'salam',1:'good morning',2:'thanks',3:'ana',4:'anta',5:'ante',6:'hua', | |
| 7:'hea',8:'antm',9:'hm',10:'name',11:'how r u',12:'thanks god',13:'happy', | |
| 14:'sad',15:'angry',16:'good',17:'bad',18:'tired',19:'sick',20:'see',21:'say', | |
| 22:'talk',23:'walk',24:'went',25:'came',26:'home',27:'eat',28:'slept',29:'university', | |
| 30:'today',31:'tmrw',32:'sunday',33:'tuesday',34:'thursday',35:'friday',36:'week', | |
| 37:'month',38:'year',39:'when',40:'I know',41:'thinking',42:'forgetten',43:'love', | |
| 44:'I want',45:'helps',46:'not allowed',47:'agree',48:'together',49:'different'} | |
| load_model_and_preprocessing() | |
| # MediaPipe setup | |
| mp_hands = mp.solutions.hands | |
| hands = mp_hands.Hands(static_image_mode=True, max_num_hands=2) | |
| def extract_hand_features(image): | |
| data_aux = np.zeros(FEATURE_LENGTH, dtype=np.float32) | |
| image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) | |
| results = hands.process(image_rgb) | |
| if not results.multi_hand_landmarks: | |
| return None | |
| for hand_idx, hand_landmarks in enumerate(results.multi_hand_landmarks): | |
| if hand_idx >= 2: break | |
| min_x = min([lm.x for lm in hand_landmarks.landmark]) | |
| min_y = min([lm.y for lm in hand_landmarks.landmark]) | |
| base_idx = hand_idx * 84 | |
| for i, lm in enumerate(hand_landmarks.landmark): | |
| data_aux[base_idx + i * 2] = lm.x - min_x | |
| data_aux[base_idx + i * 2 + 1] = lm.y - min_y | |
| return data_aux | |
| sequence_buffer = deque(maxlen=SEQUENCE_LENGTH) | |
| def predict_sign(image): | |
| image = np.array(image) | |
| features = extract_hand_features(image) | |
| if features is None: | |
| return "No hand detected" | |
| sequence_buffer.append(features) | |
| if len(sequence_buffer) < SEQUENCE_LENGTH: | |
| return f"Waiting for sequence: {len(sequence_buffer)}/{SEQUENCE_LENGTH}" | |
| sequence_data = np.array(list(sequence_buffer)).reshape(1, SEQUENCE_LENGTH, FEATURE_LENGTH) | |
| scaled = scaler.transform(sequence_data.reshape(-1, FEATURE_LENGTH)).reshape(1, SEQUENCE_LENGTH, FEATURE_LENGTH) | |
| prediction_scores = model.predict(scaled, verbose=0)[0] | |
| predicted_idx = np.argmax(prediction_scores) | |
| confidence = prediction_scores[predicted_idx] | |
| label = labels_dict.get(predicted_idx, "Unknown") | |
| return f"{label} ({confidence:.2f})" | |
| # Gradio interface | |
| interface = gr.Interface(fn=predict_sign, | |
| inputs=gr.Image(source="webcam", tool="editor", type="numpy"), | |
| outputs="text", | |
| title="Sign Language Recognition", | |
| description="Perform a sign and capture it. Wait for prediction...") | |
| # ✅ LAUNCH THE APP | |
| interface.launch() | |