https://merve-owlv2.hf.space/

1<!doctype html>
2<html
3	lang="en"
4	style="
5		margin: 0;
6		padding: 0;
7		min-height: 100%;
8		display: flex;
9		flex-direction: column;
10	"
11>
12	<head>
13		<meta charset="utf-8" />
14		<meta
15			name="viewport"
16			content="width=device-width, initial-scale=1, shrink-to-fit=no"
17		/>
18
19		
20		<meta property="og:url" content="https://gradio.app/" />
21		<meta property="og:type" content="website" />
22		<meta property="og:image" content="" />
23		<meta property="og:title" content="Zero-Shot Object Detection with OWLv2" />
24		<meta
25			property="og:description"
26			content=""
27		/>
28		<meta name="twitter:card" content="summary_large_image" />
29		<meta name="twitter:creator" content="@teamGradio" />
30		<meta name="twitter:title" content="Zero-Shot Object Detection with OWLv2" />
31		<meta
32			name="twitter:description"
33			content=""
34		/>
35		<meta name="twitter:image" content="" />
36
37		

37<script data-gradio-mode>
38			window.__gradio_mode__ = "app";
39			window.iFrameResizer = {
40				heightCalculationMethod: "taggedElement"
41			};
42		</script>

42
43
44		

44<script>window.gradio_config = {"version":"4.16.0","mode":"interface","app_id":2553237648562173263,"dev_mode":false,"analytics_enabled":true,"components":[{"id":5,"type":"markdown","props":{"value":"\u003ch1 style=\u0027text-align: center; margin-bottom: 1rem\u0027\u003eZero-Shot Object Detection with OWLv2\u003c/h1\u003e","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"810c5f8552642d85df14958a33f75123","api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":6,"type":"markdown","props":{"value":"Try this demo for \u003ca href=\"https://huggingface.co/docs/transformers/main/en/model_doc/owlv2\"\u003eOWLv2\u003c/a\u003e,\nintroduced in \u003ca href=\"https://arxiv.org/abs/2306.09683\"\u003eScaling Open-Vocabulary Object Detection\u003c/a\u003e.\n\n\n Compared to OWLVIT, OWLv2 performs better both in yield and performance (average precision).\nYou can use OWLv2 to query images with text descriptions of any object.\nTo use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for. You\ncan also use the score threshold slider to set a threshold to filter out low probability predictions.\n\n\nOWL-ViT is trained on text templates,\nhence you can get better predictions by querying the image with text templates used in training the original model: e.g. *\"photo of a star-spangled banner\"*,\n*\"image of a shoe\"*. Refer to the \u003ca href=\"https://arxiv.org/abs/2103.00020\"\u003eCLIP\u003c/a\u003e paper to see the full list of text templates used to augment the training data.\n\n\n\u003ca href=\"https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb\"\u003eColab demo\u003c/a\u003e","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"810c5f8552642d85df14958a33f75123","api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":7,"type":"row","props":{"variant":"default","visible":true,"equal_height":false,"name":"row"},"skip_api":true,"component_class_id":"9a37ebd52f5e3ac2d2a1b25e6c1b3eba"},{"id":8,"type":"column","props":{"scale":1,"min_width":320,"variant":"panel","visible":true,"name":"column"},"skip_api":true,"component_class_id":"cc17d07a8a70ee1001b1e05bebd9e3a3"},{"id":9,"type":"column","props":{"scale":1,"min_width":320,"variant":"default","visible":true,"name":"column"},"skip_api":true,"component_class_id":"cc17d07a8a70ee1001b1e05bebd9e3a3"},{"id":0,"type":"image","props":{"streamable":false,"image_mode":"RGB","sources":["upload","webcam","clipboard"],"type":"numpy","label":"img","show_label":true,"show_download_button":true,"container":true,"min_width":160,"visible":true,"streaming":false,"elem_classes":[],"mirror_webcam":true,"show_share_button":true,"name":"image","_selectable":false},"skip_api":false,"component_class_id":"2e3b63a2f03a47e67288237e6ff0a5fa","api_info":{"properties":{"path":{"title":"Path","type":"string"},"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Url"},"size":{"anyOf":[{"type":"integer"},{"type":"null"}],"default":null,"title":"Size"},"orig_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Orig Name"},"mime_type":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Mime Type"}},"required":["path"],"title":"FileData","type":"object"},"example_inputs":"https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png"},{"id":3,"type":"textbox","props":{"value":"","lines":1,"max_lines":20,"label":"text_queries","show_label":true,"container":true,"min_width":160,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"777333cda51df020195231508683831a","api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":1,"type":"slider","props":{"minimum":0,"maximum":1,"value":0.1,"step":0.01,"label":"score_threshold","show_label":true,"container":true,"min_width":160,"visible":true,"elem_classes":[],"name":"slider","_selectable":false},"skip_api":false,"component_class_id":"92d475377d8dbf22997635901e7c301a","api_info":{"type":"number","description":"numeric value between 0 and 1"},"example_inputs":0},{"id":10,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"8a922308b8adf2794816d4dee399dbae"},{"id":11,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"name":"row"},"skip_api":true,"component_class_id":"9a37ebd52f5e3ac2d2a1b25e6c1b3eba"},{"id":12,"type":"button","props":{"value":"Clear","variant":"secondary","visible":true,"interactive":true,"elem_classes":[],"show_api":false,"name":"button","_selectable":false},"skip_api":true,"component_class_id":"2e26b9948f0b4b16f38674f453253822"},{"id":13,"type":"button","props":{"value":"Submit","variant":"primary","visible":true,"interactive":true,"elem_classes":[],"name":"button","_selectable":false},"skip_api":true,"component_class_id":"e6d4e61f49a0e5522730f312b1fb6380"},{"id":14,"type":"column","props":{"scale":1,"min_width":320,"variant":"panel","visible":true,"name":"column"},"skip_api":true,"component_class_id":"cc17d07a8a70ee1001b1e05bebd9e3a3"},{"id":4,"type":"annotatedimage","props":{"show_legend":true,"label":"output","show_label":true,"container":true,"min_width":160,"visible":true,"elem_classes":[],"name":"annotatedimage","_selectable":false},"skip_api":false,"component_class_id":"92dedcbf4cb1d0c3ceb1140017569df1","api_info":{"$defs":{"Annotation":{"properties":{"image":{"$ref":"#/$defs/FileData"},"label":{"title":"Label","type":"string"}},"required":["image","label"],"title":"Annotation","type":"object"},"FileData":{"properties":{"path":{"title":"Path","type":"string"},"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Url"},"size":{"anyOf":[{"type":"integer"},{"type":"null"}],"default":null,"title":"Size"},"orig_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Orig Name"},"mime_type":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Mime Type"}},"required":["path"],"title":"FileData","type":"object"}},"properties":{"image":{"$ref":"#/$defs/FileData"},"annotations":{"items":{"$ref":"#/$defs/Annotation"},"title":"Annotations","type":"array"}},"required":["image","annotations"],"title":"AnnotatedImageData","type":"object"},"example_inputs":{}},{"id":15,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"name":"row"},"skip_api":true,"component_class_id":"9a37ebd52f5e3ac2d2a1b25e6c1b3eba"},{"id":16,"type":"dataset","props":{"samples":[[{"path":"/tmp/gradio/2e2ea002efaf146a880225a8fa61710dedf782b4/astronaut.png","url":null,"size":null,"orig_name":"astronaut.png","mime_type":null},"human face, rocket, star-spangled banner, nasa badge",0.11],[{"path":"/tmp/gradio/2ad19dc294cb522352dd837e946fdd5f085eb704/coffee.png","url":null,"size":null,"orig_name":"coffee.png","mime_type":null},"coffee mug, spoon, plate",0.1],[{"path":"/tmp/gradio/96798f025e7f7634e1c7f361c044d5d751a546fb/butterflies.jpeg","url":null,"size":null,"orig_name":"butterflies.jpeg","mime_type":null},"orange butterfly",0.3]],"headers":["img","text_queries","score_threshold"],"type":"index","samples_per_page":10,"visible":true,"elem_classes":[],"container":true,"min_width":160,"name":"dataset","_selectable":false,"components":["image","textbox","slider"],"component_props":[{"height":null,"width":null,"image_mode":"RGB","sources":["upload","webcam","clipboard"],"type":"numpy","label":"img","show_label":true,"show_download_button":true,"container":true,"scale":null,"min_width":160,"interactive":null,"visible":true,"streaming":false,"elem_id":null,"elem_classes":[],"mirror_webcam":true,"show_share_button":true},{"lines":1,"max_lines":20,"placeholder":null,"label":"text_queries","info":null,"show_label":true,"container":true,"scale":null,"min_width":160,"interactive":null,"visible":true,"elem_id":null,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","text_align":null,"rtl":false,"show_copy_button":false},{"minimum":0,"maximum":1,"step":0.01,"label":"score_threshold","info":null,"show_label":true,"container":true,"scale":null,"min_width":160,"interactive":null,"visible":true,"elem_id":null,"elem_classes":[]}],"component_ids":[0,3,1]},"skip_api":false,"component_class_id":"165924da27f1699791bde1664a7e9e7e","api_info":{"type":"integer","description":"index of selected example"},"example_inputs":0}],"css":null,"js":null,"head":null,"title":"Zero-Shot Object Detection with OWLv2","space_id":"merve/owlv2","enable_queue":true,"show_error":false,"show_api":true,"is_colab":false,"stylesheets":["https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600\u0026display=swap","https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;600\u0026display=swap"],"theme":"default","protocol":"sse_v1","layout":{"id":2,"children":[{"id":5},{"id":6},{"id":7,"children":[{"id":8,"children":[{"id":9,"children":[{"id":0},{"id":10,"children":[{"id":3},{"id":1}]}]},{"id":11,"children":[{"id":12},{"id":13}]}]},{"id":14,"children":[{"id":4},{"id":15,"children":[]}]}]},{"id":16}]},"dependencies":[{"targets":[[13,"click"],[3,"submit"]],"inputs":[0,3,1],"outputs":[4],"backend_fn":true,"js":null,"queue":null,"api_name":"predict","scroll_to_output":false,"show_progress":"full","every":null,"batch":false,"max_batch_size":4,"cancels":[],"types":{"continuous":false,"generator":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true},{"targets":[[12,"click"]],"inputs":[],"outputs":[0,3,1,4],"backend_fn":false,"js":"() =\u003e [null, null, 0, null]","queue":false,"api_name":"js_fn","scroll_to_output":false,"show_progress":"full","every":null,"batch":false,"max_batch_size":4,"cancels":[],"types":{"continuous":false,"generator":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":false},{"targets":[[12,"click"]],"inputs":[],"outputs":[9],"backend_fn":false,"js":"() =\u003e [{\"variant\": null, \"visible\": true, \"__type__\": \"update\"}]\n            ","queue":false,"api_name":"js_fn_1","scroll_to_output":false,"show_progress":"full","every":null,"batch":false,"max_batch_size":4,"cancels":[],"types":{"continuous":false,"generator":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":false},{"targets":[[16,"click"]],"inputs":[16],"outputs":[0,3,1,4],"backend_fn":true,"js":null,"queue":false,"api_name":"load_example","scroll_to_output":false,"show_progress":"hidden","every":null,"batch":false,"max_batch_size":4,"cancels":[],"types":{"continuous":false,"generator":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":false}],"root":"https://merve-owlv2.hf.space/--replicas/bm2wx"};</script>

44
45
46		<link rel="preconnect" href="https://fonts.googleapis.com" />
47		<link
48			rel="preconnect"
49			href="https://fonts.gstatic.com"
50			crossorigin="anonymous"
51		/>
52		

52<script
53			src="https://cdnjs.cloudflare.com/ajax/libs/iframe-resizer/4.3.9/iframeResizer.contentWindow.min.js"
54			async
55		></script>

55
56		

56<script type="module" crossorigin src="./assets/index-546f83db.js"></script>

56
57		<link rel="stylesheet" href="./assets/index-20519b4d.css">
58	</head>
59
60	<body
61		style="
62			width: 100%;
63			margin: 0;
64			padding: 0;
65			display: flex;
66			flex-direction: column;
67			flex-grow: 1;
68		"
69	>
70		<gradio-app
71			control_page_title="true"
72			embed="false"
73			eager="true"
74			style="display: flex; flex-direction: column; flex-grow: 1"
75		>
76		</gradio-app>
77		

77<script>
78			const ce = document.getElementsByTagName("gradio-app");
79			if (ce[0]) {
80				ce[0].addEventListener("domchange", () => {
81					document.body.style.padding = "0";
82				});
83				document.body.style.padding = "0";
84			}
85		</script>

85
86	</body>
87</html>