Spaces:
Sleeping
Sleeping
| import os | |
| import tarfile | |
| import wget | |
| import numpy as np | |
| import tensorflow as tf | |
| from huggingface_hub import snapshot_download | |
| import gradio as gr | |
| from object_detection.utils import label_map_util | |
| from object_detection.utils import visualization_utils as viz_utils | |
| # Constants | |
| REPO_ID = "wongshennan/iti107_model" | |
| PATH_TO_LABELS = 'data/label_map.pbtxt' | |
| # Load category index | |
| category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True) | |
| def pil_image_as_numpy_array(pil_img): | |
| """Convert PIL image to numpy array.""" | |
| img_array = tf.keras.utils.img_to_array(pil_img) | |
| img_array = np.expand_dims(img_array, axis=0) | |
| return img_array | |
| def load_model(): | |
| """Load model from Hugging Face Hub.""" | |
| download_dir = snapshot_download(REPO_ID) | |
| saved_model_dir = os.path.join(download_dir, "saved_model") | |
| return tf.saved_model.load(saved_model_dir) | |
| def load_model2(): | |
| """Load model from a tar.gz file.""" | |
| wget.download("https://nyp-aicourse.s3-ap-southeast-1.amazonaws.com/pretrained-models/balloon_model.tar.gz") | |
| tarfile.open("balloon_model.tar.gz").extractall() | |
| model_dir = 'saved_model' | |
| return tf.saved_model.load(str(model_dir)) | |
| def predict(pil_img): | |
| """Predict method for Gradio interface.""" | |
| image_np = pil_image_as_numpy_array(pil_img) | |
| return detect_and_visualize(image_np) | |
| def detect_and_visualize(image_np): | |
| """Helper function to run object detection and visualize results.""" | |
| results = detection_model(image_np) | |
| 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) | |
| return tf.keras.utils.array_to_img(image_np_with_detections[0]) | |
| # Load the model | |
| detection_model = load_model() | |
| # Launch Gradio Interface | |
| gr.Interface(fn=predict, | |
| inputs=gr.Image(type="pil"), | |
| outputs=gr.Image(type="pil") | |
| ).launch(share=True) | |