Spaces:
Sleeping
Sleeping
Commit
•
c30c3c6
1
Parent(s):
b6f2026
Update app.py
Browse files
app.py
CHANGED
|
@@ -40,7 +40,7 @@ def yolov8_inference(
|
|
| 40 |
|
| 41 |
|
| 42 |
return annotated_image
|
| 43 |
-
|
| 44 |
image_input = gr.inputs.Image() # Adjust the shape according to your requirements
|
| 45 |
|
| 46 |
inputs = [
|
|
@@ -53,16 +53,87 @@ inputs = [
|
|
| 53 |
|
| 54 |
outputs = gr.Image(type="filepath", label="Output Image")
|
| 55 |
title = "Amazon Products Demo"
|
|
|
|
| 56 |
import os
|
| 57 |
examples = [["ex1.png", 0.5, 0.45],
|
| 58 |
["tu3.jpg", 0.5, 0.45],
|
| 59 |
]
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
|
| 42 |
return annotated_image
|
| 43 |
+
'''
|
| 44 |
image_input = gr.inputs.Image() # Adjust the shape according to your requirements
|
| 45 |
|
| 46 |
inputs = [
|
|
|
|
| 53 |
|
| 54 |
outputs = gr.Image(type="filepath", label="Output Image")
|
| 55 |
title = "Amazon Products Demo"
|
| 56 |
+
'''
|
| 57 |
import os
|
| 58 |
examples = [["ex1.png", 0.5, 0.45],
|
| 59 |
["tu3.jpg", 0.5, 0.45],
|
| 60 |
]
|
| 61 |
+
outputs_images = [
|
| 62 |
+
["1.jpg"], # First example: an output image for the cat example
|
| 63 |
+
["2.jpg"] # Second example: an output image for the dog exam
|
| 64 |
+
]
|
| 65 |
+
|
| 66 |
+
readme_html = """
|
| 67 |
+
<html>
|
| 68 |
+
<head>
|
| 69 |
+
<style>
|
| 70 |
+
.description {
|
| 71 |
+
margin: 20px;
|
| 72 |
+
padding: 10px;
|
| 73 |
+
border: 1px solid #ccc;
|
| 74 |
+
}
|
| 75 |
+
</style>
|
| 76 |
+
</head>
|
| 77 |
+
<body>
|
| 78 |
+
<div class="description">
|
| 79 |
+
<p><strong>More details:</strong></p>
|
| 80 |
+
<p>We present a demo for performing object segmentation using a model trained on Amazon's ARMBench dataset. The model was trained on over 37,000 training images and validated on 4,425 images.</p>
|
| 81 |
+
<p><strong>Usage:</strong></p>
|
| 82 |
+
<p>You can use our demo by uploading your product image, and it will provide you with a segmented image.</p>
|
| 83 |
+
<p><strong>Dataset:</strong></p>
|
| 84 |
+
<p>-The model was trained on the ARMBench segmentation dataset, which comprises more than 50,000 images.</p>
|
| 85 |
+
<ul>
|
| 86 |
+
<li>Paper: ARMBench: An object-centric benchmark dataset for robotic manipulation</li>
|
| 87 |
+
<li>Authors: Chaitanya Mitash, Fan Wang, Shiyang Lu, Vikedo Terhuja, Tyler Garaas, Felipe Polido, Manikantan Nambi</li>
|
| 88 |
+
</ul>
|
| 89 |
+
<p><strong>License:</strong> This dataset is made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0).</p>
|
| 90 |
+
<p>To access and download this dataset, please follow this link: <a href=" https://www.amazon.science/blog/amazon-releases-largest-dataset-for-training-pick-and-place-robots." target="_blank">Dataset Download</a></p>
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
</body>
|
| 94 |
+
</html>
|
| 95 |
+
"""
|
| 96 |
+
with gr.Blocks() as demo:
|
| 97 |
+
gr.Markdown(
|
| 98 |
+
"""
|
| 99 |
+
<div style="text-align: center;">
|
| 100 |
+
<h1> Amazon Products Demo</h1>
|
| 101 |
+
Powered by <a href="https://Tuba.ai">Tuba</a>
|
| 102 |
+
</div>
|
| 103 |
+
"""
|
| 104 |
+
)
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
# Define the input components and add them to the layout
|
| 108 |
+
with gr.Row():
|
| 109 |
+
image_input = gr.inputs.Image()
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
outputs = gr.Image(type="filepath", label="Output Image")
|
| 113 |
+
|
| 114 |
+
# Define the output component and add it to the layout
|
| 115 |
+
with gr.Row():
|
| 116 |
+
conf_slider=gr.Slider(minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold" )
|
| 117 |
+
with gr.Row():
|
| 118 |
+
IOU_Slider=gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold")
|
| 119 |
+
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
button = gr.Button("Run")
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
# Define the event listener that connects the input and output components and triggers the function
|
| 127 |
+
button.click(fn=yolov8_inference, inputs=[image_input, conf_slider,IOU_Slider], outputs=outputs, api_name="yolov8_inference")
|
| 128 |
+
|
| 129 |
+
gr.Examples(
|
| 130 |
+
fn=yolov8_inference,
|
| 131 |
+
examples=examples,
|
| 132 |
+
inputs=[image_input, conf_slider,IOU_Slider],
|
| 133 |
+
outputs=[outputs]
|
| 134 |
+
)
|
| 135 |
+
# gr.Examples(inputs=examples, outputs=outputs_images)
|
| 136 |
+
# Add the description below the layout
|
| 137 |
+
gr.Markdown(readme_html)
|
| 138 |
+
# Launch the app
|
| 139 |
+
demo.launch(share=False)
|