Update app.py

app.py

@@ -1,10 +1,12 @@
+import matplotlib.pyplot as plt
 import numpy as np
 from six import BytesIO
 from PIL import Image
-
 import tensorflow as tf
 from object_detection.utils import label_map_util
 from object_detection.utils import visualization_utils as viz_utils
+from object_detection.utils import ops as utils_op
+import tarfile
 import wget 
 import gradio as gr
 from huggingface_hub import snapshot_download
@@ -81,172 +83,16 @@ def predict2(image_np):
     
     return result_pil_img
 
-# import cv2
-
-# def predict_video(video_path):
-#     cap = cv2.VideoCapture(video_path)
-#     frame_width = int(cap.get(3))
-#     frame_height = int(cap.get(4))
-
-#     # Define the codec and create a video writer object
-#     out = cv2.VideoWriter('output.avi', cv2.VideoWriter_fourcc('M','J','P','G'), 10, (frame_width, frame_height))
-
-#     while cap.isOpened():
-#         ret, frame = cap.read()
-#         if not ret:
-#             break
-
-#         # Convert the frame to PIL image
-#         pil_image = Image.fromarray(frame)
-        
-#         # Perform object detection on the frame
-#         result_pil_img = predict(pil_image)
-
-#         # Convert the result back to a NumPy array
-#         result_np_img = tf.keras.utils.img_to_array(result_pil_img)
-
-#         # Write the frame with detected objects to the video output
-#         out.write(result_np_img.astype('uint8'))
-
-#     # Release the video capture and writer objects
-#     cap.release()
-#     out.release()
-
-#     return "output.avi"
-
-
 
-# REPO_ID = "Louisw3399/burgerorfriesdetector"
-# detection_model = load_model()
-# # pil_image = Image.open(image_path)
-# # image_arr = pil_image_as_numpy_array(pil_image)
-
-# # predicted_img = predict(image_arr)
-# # predicted_img.save('predicted.jpg')
-
-# gr.Interface(fn=predict,
-#              inputs=gr.Image(type="pil"),
-#              outputs=gr.Image(type="pil")
-#              ).launch(share=True)
-
-# gr.Interface(
-#     fn=predict_video,
-#     inputs=gr.Video(type="file", label="Upload a video"),
-#     outputs=gr.Video(type="file", label="Download the processed video")
-# ).launch(share=True)
-
-# import numpy as np
-# from six import BytesIO
-# from PIL import Image
-# import tensorflow as tf
-# from object_detection.utils import label_map_util
-# from object_detection.utils import visualization_utils as viz_utils
-# from object_detection.utils import ops as utils_op
-# from huggingface_hub import snapshot_download
-# import gradio as gr
-# import cv2
-# import os
-
-# # Install TensorFlow within the Hugging Face environment
-# os.system('pip install tensorflow')
-
-# # Now you can import TensorFlow
-# import tensorflow as tf
-
-# PATH_TO_LABELS = 'data/label_map.pbtxt'   
-# category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)
-
-# def pil_image_as_numpy_array(pilimg):
-#     img_array = tf.keras.utils.img_to_array(pilimg)
-#     img_array = np.expand_dims(img_array, axis=0)
-#     return img_array
-    
-# def load_image_into_numpy_array(path):
-#     image_data = tf.io.gfile.GFile(path, 'rb').read()
-#     image = Image.open(BytesIO(image_data))
-#     return pil_image_as_numpy_array(image)            
-
-# def load_model():
-#     download_dir = snapshot_download(REPO_ID)
-#     saved_model_dir = os.path.join(download_dir, "saved_model")
-#     detection_model = tf.saved_model.load(saved_model_dir)
-#     return detection_model
-
-# def predict(pilimg):
-#     image_np = pil_image_as_numpy_array(pilimg)
-#     return predict_objects(image_np)
-
-# def predict_objects(image_np):
-#     results = detection_model(image_np)
-
-#     # Different object detection models may have additional results
-#     result = {key: value.numpy() for key, value in results.items()}
-    
-#     label_id_offset = 0
-#     image_np_with_detections = image_np.copy()
-
-#     viz_utils.visualize_boxes_and_labels_on_image_array(
-#         image_np_with_detections[0],
-#         result['detection_boxes'][0],
-#         (result['detection_classes'][0] + label_id_offset).astype(int),
-#         result['detection_scores'][0],
-#         category_index,
-#         use_normalized_coordinates=True,
-#         max_boxes_to_draw=200,
-#         min_score_thresh=0.60,
-#         agnostic_mode=False,
-#         line_thickness=2
-#     )
-
-#     result_pil_img = tf.keras.utils.array_to_img(image_np_with_detections[0])
-#     return result_pil_img
-
-# def predict_video(video_path):
-#     cap = cv2.VideoCapture(video_path)
-#     frame_width = int(cap.get(3))
-#     frame_height = int(cap.get(4))
-
-#     # Define the codec and create a video writer object
-#     out = cv2.VideoWriter('output.avi', cv2.VideoWriter_fourcc('M','J','P','G'), 10, (frame_width, frame_height))
-
-#     while cap.isOpened():
-#         ret, frame = cap.read()
-#         if not ret:
-#             break
-
-#         # Convert the frame to PIL image
-#         pil_image = Image.fromarray(frame)
-        
-#         # Perform object detection on the frame
-#         result_pil_img = predict_objects(frame)
-
-#         # Convert the result back to a NumPy array
-#         result_np_img = tf.keras.utils.img_to_array(result_pil_img)
-
-#         # Write the frame with detected objects to the video output
-#         out.write(result_np_img.astype('uint8'))
-
-#     # Release the video capture and writer objects
-#     cap.release()
-#     out.release()
-
-#     return "output.avi"
-
-# REPO_ID = "Louisw3399/burgerorfriesdetector"
-# detection_model = load_model()
-
-# gr.Interface(
-#     fn=predict,
-#     inputs=gr.Image(type="pil"),
-#     outputs=gr.Image(type="pil"),
-#     label="Image Object Detection"
-# ).launch(share=True)
-
-# gr.Interface(
-#     fn=predict_video,
-#     inputs=gr.Video(type="file", label="Upload a video"),
-#     outputs=gr.Video(type="file", label="Download the processed video"),
-#     label="Video Object Detection"
-# ).launch(share=True)
+REPO_ID = "Louisw3399/burgerorfriesdetector"
+detection_model = load_model()
+# pil_image = Image.open(image_path)
+# image_arr = pil_image_as_numpy_array(pil_image)
 
+# predicted_img = predict(image_arr)
+# predicted_img.save('predicted.jpg')
 
+gr.Interface(fn=predict,
+             inputs=gr.Image(type="pil"),
+             outputs=gr.Image(type="pil")
+             ).launch(share=True)