Spaces:
Runtime error
Runtime error
File size: 3,780 Bytes
fee6d38 |
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 |
import torch
from transformers import pipeline
from PIL import Image
import cv2
import numpy as np
from random import choice
import io
detector50 = pipeline(model="facebook/detr-resnet-50")
detector101 = pipeline(model="facebook/detr-resnet-101")
import gradio as gr
COLORS = ["#ff7f7f", "#ff7fbf", "#ff7fff", "#bf7fff",
"#7f7fff", "#7fbfff", "#7fffff", "#7fffbf",
"#7fff7f", "#bfff7f", "#ffff7f", "#ffbf7f"]
fdic = {
"family" : "Impact",
"style" : "italic",
"size" : 15,
"color" : "yellow",
"weight" : "bold"
}
def get_figure(in_pil_img, in_results):
# Convert PIL image to OpenCV format
img_cv2 = np.array(in_pil_img)
img_cv2 = cv2.cvtColor(img_cv2, cv2.COLOR_RGB2BGR)
for prediction in in_results:
selected_color = choice(COLORS)
color = tuple(int(selected_color[i:i+2], 16) for i in (1, 3, 5)) # Convert hex color to RGB tuple
x, y = prediction['box']['xmin'], prediction['box']['ymin']
w, h = prediction['box']['xmax'] - prediction['box']['xmin'], prediction['box']['ymax'] - prediction['box']['ymin']
# Draw bounding box using OpenCV
img_cv2 = cv2.rectangle(img_cv2, (x, y), (x+w, y+h), color, 2)
text = f"{prediction['label']}: {round(prediction['score']*100, 1)}%"
img_cv2 = cv2.putText(img_cv2, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, color, 2)
# Convert back to PIL format
img_pil = Image.fromarray(cv2.cvtColor(img_cv2, cv2.COLOR_BGR2RGB))
return img_pil
def infer(model, in_pil_img):
results = None
if model == "detr-resnet-101":
results = detector101(in_pil_img)
else:
results = detector50(in_pil_img)
output_pil_img = get_figure(in_pil_img, results)
output_pil_img.save("output.jpg")
return output_pil_img
with gr.Blocks(title="DETR Object Detection using openCV",
css=".gradio-container {background:lightyellow;}"
) as demo:
#sample_index = gr.State([])
gr.HTML("""<div style="font-family:'Times New Roman', 'Serif'; font-size:16pt; font-weight:bold; text-align:center; color:royalblue;">ObjecTron🪄</div>""")
gr.HTML("""<div style="font-family:'Times New Roman', 'Serif'; font-size:16pt; font-weight:bold; text-align:center; color:royalblue;">
A object detection app using OpenCV, Huggingface-transformers, detr-resnet and Gradio </div>""")
gr.HTML("""<h4 style="color:navy;">1. Select a model.</h4>""")
model = gr.Radio(["detr-resnet-50", "detr-resnet-101"], value="detr-resnet-50", label="Model name")
gr.HTML("""<br/>""")
gr.HTML("""<h4 style="color:navy;">2-a. Select an example below</h4>""")
gr.HTML("""<h4 style="color:navy;">2-b. Or upload an image by clicking on the canvas.</h4>""")
with gr.Row():
input_image = gr.Image(label="Input image", type="pil")
output_image = gr.Image(label="Output image with predicted instances", type="pil")
gr.Examples(['samples/god.jpg','samples/road.jpg','samples/cats.jpg','samples/detectron.png','samples/dogandcat.jpg'], inputs=input_image)
gr.HTML("""<br/>""")
gr.HTML("""<h4 style="color:navy;">3. Then, click the button below to predict and see the magic!!!</h4>""")
send_btn = gr.Button("Expecto Patronum 🪄")
send_btn.click(fn=infer, inputs=[model, input_image], outputs=[output_image])
gr.HTML("""<br/>""")
gr.HTML("""<h4 style="color:navy;">Reference</h4>""")
gr.HTML("""<ul>""")
gr.HTML("""<li><a href="https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_attention.ipynb" target="_blank">Hands-on tutorial for DETR by facebookresearch</a>""")
gr.HTML("""</ul>""")
#demo.queue()
demo.launch(debug=True) |