File size: 5,582 Bytes
8e909d4 f99c7e8 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 611a237 8e909d4 192a5c6 8e909d4 192a5c6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
# import gradio as gr
# import spaces
# from huggingface_hub import hf_hub_download
# def download_models(model_id):
# hf_hub_download("SakshiRathi77/void-space-detection", filename=f"{model_id}", local_dir=f"./")
# return f"./{model_id}"
# @spaces.GPU
# def yolov9_inference(img_path, model_id, image_size, conf_threshold, iou_threshold):
# """
# Load a YOLOv9 model, configure it, perform inference on an image, and optionally adjust
# the input size and apply test time augmentation.
# :param model_path: Path to the YOLOv9 model file.
# :param conf_threshold: Confidence threshold for NMS.
# :param iou_threshold: IoU threshold for NMS.
# :param img_path: Path to the image file.
# :param size: Optional, input size for inference.
# :return: A tuple containing the detections (boxes, scores, categories) and the results object for further actions like displaying.
# """
# # Import YOLOv9
# import yolov9
# # Load the model
# model_path = download_models(model_id)
# model = yolov9.load(model_path, device="cuda:0")
# # Set model parameters
# model.conf = conf_threshold
# model.iou = iou_threshold
# # Perform inference
# results = model(img_path, size=image_size)
# # Optionally, show detection bounding boxes on image
# output = results.render()
# return output[0]
# def app():
# with gr.Blocks():
# with gr.Row():
# with gr.Column():
# img_path = gr.Image(type="filepath", label="Image")
# model_path = gr.Dropdown(
# label="Model",
# choices=[
# "state_dict.pt"
# ],
# value="state_dict.pt",
# )
# image_size = gr.Slider(
# label="Image Size",
# minimum=320,
# maximum=1280,
# step=32,
# value=640,
# )
# conf_threshold = gr.Slider(
# label="Confidence Threshold",
# minimum=0.1,
# maximum=1.0,
# step=0.1,
# value=0.4,
# )
# iou_threshold = gr.Slider(
# label="IoU Threshold",
# minimum=0.1,
# maximum=1.0,
# step=0.1,
# value=0.5,
# )
# yolov9_infer = gr.Button(value="Inference")
# with gr.Column():
# output_numpy = gr.Image(type="numpy",label="Output")
# yolov9_infer.click(
# fn=yolov9_inference,
# inputs=[
# img_path,
# model_path,
# image_size,
# conf_threshold,
# iou_threshold,
# ],
# outputs=[output_numpy],
# )
# # gr.Examples(
# # examples=[
# # [
# # "data/zidane.jpg",
# # "gelan-e.pt",
# # 640,
# # 0.4,
# # 0.5,
# # ],
# # [
# # "data/huggingface.jpg",
# # "yolov9-c.pt",
# # 640,
# # 0.4,
# # 0.5,
# # ],
# # ],
# # fn=yolov9_inference,
# # inputs=[
# # img_path,
# # model_path,
# # image_size,
# # conf_threshold,
# # iou_threshold,
# # ],
# # outputs=[output_numpy],
# # cache_examples=True,
# # )
# gradio_app = gr.Blocks()
# with gradio_app:
# gr.HTML(
# """
# <h1 style='text-align: center'>
# YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
# </h1>
# """)
# gr.HTML(
# """
# <h3 style='text-align: center'>
# Follow me for more!
# </h3>
# """)
# with gr.Row():
# with gr.Column():
# app()
# gradio_app.launch(debug=True)
# make sure you have the following dependencies
import gradio as gr
import torch
from torchvision import transforms
from PIL import Image
# Load the YOLOv9 model
model_path = "best.pt" # Replace with the path to your YOLOv9 model
model = torch.load(model_path)
# Define preprocessing transforms
preprocess = transforms.Compose([
transforms.Resize((640, 640)), # Resize image to model input size
transforms.ToTensor(), # Convert image to tensor
])
# Define a function to perform inference
def detect_void(image):
# Preprocess the input image
image = Image.fromarray(image)
image = preprocess(image).unsqueeze(0) # Add batch dimension
# Perform inference
with torch.no_grad():
output = model(image)
# Post-process the output if needed
# For example, draw bounding boxes on the image
# Convert the image back to numpy array
# and return the result
return output.squeeze().numpy()
# Define Gradio interface components
input_image = gr.inputs.Image(shape=(640, 640), label="Input Image")
output_image = gr.outputs.Image(label="Output Image")
# Create Gradio interface
gr.Interface(fn=detect_void, inputs=input_image, outputs=output_image, title="Void Detection App").launch()
|