app.py

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
import os 
import cv2
from tqdm import tqdm

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 = None
    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(model_repo_id):
    download_dir = snapshot_download(model_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 predict2(image_np)

def predict2(image_np):

    results = detection_model(image_np)

    # different object detection models 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=.60,
        agnostic_mode=False,
        line_thickness=2)

    result_pil_img2 = tf.keras.utils.array_to_img(image_np_with_detections[0])
    
    return result_pil_img2

def predict3(pilimg):

    image_np = pil_image_as_numpy_array(pilimg)
    return predict4(image_np)

def predict4(image_np):

    results = detection_model2(image_np)

    # different object detection models 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=.60,
        agnostic_mode=False,
        line_thickness=2)

    result_pil_img4 = tf.keras.utils.array_to_img(image_np_with_detections[0])
    
    return result_pil_img4

def detect_video(video):
    # Create a video capture object
    cap = cv2.VideoCapture(video)

    # Process frames in a loop
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break

        # Expand dimensions since model expects images to have shape: [1, None, None, 3]
        image_np_expanded = np.expand_dims(frame, axis=0)

        # Run inference
        output_dict = model(image_np_expanded)

        # Extract detections
        boxes = output_dict['detection_boxes'][0].numpy()
        scores = output_dict['detection_scores'][0].numpy()
        classes = output_dict['detection_classes'][0].numpy().astype(np.int64)

        # Draw bounding boxes and labels
        image_np_with_detections = viz_utils.visualize_boxes_and_labels_on_image_array(
            frame,
            boxes,
            classes,
            scores,
            category_index,
            use_normalized_coordinates=True,
            max_boxes_to_draw=20,
            min_score_thresh=.5,
            agnostic_mode=False)

        # Yield the processed frame
        yield image_np_with_detections

    # Release resources
    cap.release()

a = os.path.join(os.path.dirname(__file__), "data/c_base_detected.mp4")  # Video
b = os.path.join(os.path.dirname(__file__), "data/c_tuned_detected.mp4")  # Video

def video_demo(video1, video2):
    return [video1, video2]

label_id_offset = 0    
REPO_ID = "apailang/mytfodmodel"
detection_model = load_model(REPO_ID)
REPO_ID2 = "apailang/mytfodmodeltuned"
detection_model2 = load_model(REPO_ID2)

samples_folder = 'data'
# 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')

test1 = os.path.join(os.path.dirname(__file__), "data/test1.jpeg")  
test2 = os.path.join(os.path.dirname(__file__), "data/test2.jpeg")  
test3 = os.path.join(os.path.dirname(__file__), "data/test3.jpeg")  
test4 = os.path.join(os.path.dirname(__file__), "data/test4.jpeg")
test5 = os.path.join(os.path.dirname(__file__), "data/test5.jpeg")
test6 = os.path.join(os.path.dirname(__file__), "data/test6.jpeg")
test7 = os.path.join(os.path.dirname(__file__), "data/test7.jpeg")
test8 = os.path.join(os.path.dirname(__file__), "data/test8.jpeg")
test9 = os.path.join(os.path.dirname(__file__), "data/test9.jpeg")
test10 = os.path.join(os.path.dirname(__file__), "data/test10.jpeg")
test11 = os.path.join(os.path.dirname(__file__), "data/test11.jpeg")
test12 = os.path.join(os.path.dirname(__file__), "data/test12.jpeg")

base_image = gr.Interface(
    fn=predict,
    inputs=gr.Image(type="pil"),
    outputs=gr.Image(type="pil"),
    title="Luffy and Chopper face detection (Base mobile net model)",
    description="Upload a Image for prediction or click on below examples",
    examples=[[test1],[test2],[test3],[test4],[test5],[test6],[test7],[test8],[test9],[test10],[test11],[test12],],
    cache_examples=True
    )#.launch(share=True)

tuned_image = gr.Interface(
    fn=predict3,
    inputs=gr.Image(type="pil"),
    outputs=gr.Image(type="pil"),
    title="Luffy and Chopper face detection (tuned mobile net model)",
    description="Upload a Image for prediction or click on below examples. Mobile net tuned with data Augmentation",
    examples=[[test1],[test2],[test3],[test4],[test5],[test6],[test7],[test8],[test9],[test10],[test11],[test12],],
    cache_examples=True
    )#.launch(share=True)



# a = os.path.join(os.path.dirname(__file__), "data/a.mp4")  # Video
# b = os.path.join(os.path.dirname(__file__), "data/b.mp4")  # Video
# c = os.path.join(os.path.dirname(__file__), "data/c.mp4")  # Video

# video_out_file = os.path.join(samples_folder,'detected' + '.mp4')

# stt_demo = gr.Interface(
#     fn=display_two_videos,
#     inputs=gr.Video(),
#     outputs=gr.Video(type="mp4",label="Detected Video"),
#     examples=[
#         [a],
#         [b],
#         [c],
#     ],
#     cache_examples=False
# )



video = gr.Interface(
    fn=video_demo,
    inputs=[gr.Video(label="base model Video"),gr.Textbox(label="tuned model Video")],
    outputs=[gr.Video(label="base model"), gr.Video(label="Tuned model")],  # Specify video outputs
    examples=[
        [a, b]
    ],
    title="Comparing base vs tuned detected video",
    description="using SSD mobile net V2 320x320. Model has been customed trained to detect Character of Luffy and Chopper"
)

demo = gr.TabbedInterface([base_image,tuned_image, video], ["Image (Base Model)","Image (Tuned Model)", "Display Detected Video"])


if __name__ == "__main__":
    demo.launch()