@huggingface/tasks 0.2.0 → 0.2.2

package/src/tasks/zero-shot-object-detection/data.ts

@@ -0,0 +1,62 @@
+import type { TaskDataCustom } from "..";
+
+const taskData: TaskDataCustom = {
+	datasets: [],
+	demo: {
+		inputs: [
+			{
+				filename: "zero-shot-object-detection-input.jpg",
+				type: "img",
+			},
+			{
+				label: "Classes",
+				content: "cat, dog, bird",
+				type: "text",
+			},
+		],
+		outputs: [
+			{
+				filename: "zero-shot-object-detection-output.jpg",
+				type: "img",
+			},
+		],
+	},
+	metrics: [
+		{
+			description:
+				"The Average Precision (AP) metric is the Area Under the PR Curve (AUC-PR). It is calculated for each class separately",
+			id: "Average Precision",
+		},
+		{
+			description: "The Mean Average Precision (mAP) metric is the overall average of the AP values",
+			id: "Mean Average Precision",
+		},
+		{
+			description:
+				"The APα metric is the Average Precision at the IoU threshold of a α value, for example, AP50 and AP75",
+			id: "APα",
+		},
+	],
+	models: [
+		{
+			description: "Solid zero-shot object detection model that uses CLIP as backbone.",
+			id: "google/owlvit-base-patch32",
+		},
+		{
+			description: "The improved version of the owlvit model.",
+			id: "google/owlv2-base-patch16-ensemble",
+		},
+	],
+	spaces: [
+		{
+			description: "A demo to try the state-of-the-art zero-shot object detection model, OWLv2.",
+			id: "merve/owlv2",
+		},
+	],
+	summary:
+		"Zero-shot object detection is a computer vision task to detect objects and their classes in images, without any prior training or knowledge of the classes. Zero-shot object detection models receive an image as input, as well as a list of candidate classes, and output the bounding boxes and labels where the objects have been detected.",
+	widgetModels: [],
+	youtubeId: "",
+};
+
+export default taskData;

package/src/tasks/zero-shot-object-detection/inference.ts

@@ -0,0 +1,66 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Zero Shot Object Detection inference
+ */
+export interface ZeroShotObjectDetectionInput {
+	/**
+	 * The input image data, with candidate labels
+	 */
+	data: ZeroShotObjectDetectionInputData;
+	/**
+	 * Additional inference parameters
+	 */
+	parameters?: {
+		[key: string]: unknown;
+	};
+	[property: string]: unknown;
+}
+/**
+ * The input image data, with candidate labels
+ */
+export interface ZeroShotObjectDetectionInputData {
+	/**
+	 * The candidate labels for this image
+	 */
+	candidateLabels: string[];
+	/**
+	 * The image data to generate bounding boxes from
+	 */
+	image: unknown;
+	[property: string]: unknown;
+}
+/**
+ * The predicted bounding box. Coordinates are relative to the top left corner of the input
+ * image.
+ */
+export interface BoundingBox {
+	xmax: number;
+	xmin: number;
+	ymax: number;
+	ymin: number;
+	[property: string]: unknown;
+}
+export type ZeroShotObjectDetectionOutput = ZeroShotObjectDetectionOutputElement[];
+/**
+ * Outputs of inference for the Zero Shot Object Detection task
+ */
+export interface ZeroShotObjectDetectionOutputElement {
+	/**
+	 * The predicted bounding box. Coordinates are relative to the top left corner of the input
+	 * image.
+	 */
+	box: BoundingBox;
+	/**
+	 * A candidate label
+	 */
+	label: string;
+	/**
+	 * The associated score / probability
+	 */
+	score: number;
+	[property: string]: unknown;
+}

package/src/tasks/zero-shot-object-detection/spec/input.json

@@ -0,0 +1,40 @@
+{
+	"$id": "/inference/schemas/zero-shot-object-detection/input.json",
+	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Inputs for Zero Shot Object Detection inference",
+	"title": "ZeroShotObjectDetectionInput",
+	"type": "object",
+	"properties": {
+		"data": {
+			"description": "The input image data, with candidate labels",
+			"type": "object",
+			"title": "ZeroShotObjectDetectionInputData",
+			"properties": {
+				"image": {
+					"description": "The image data to generate bounding boxes from"
+				},
+				"candidateLabels": {
+					"description": "The candidate labels for this image",
+					"type": "array",
+					"items": {
+						"type": "string"
+					}
+				}
+			},
+			"required": ["image", "candidateLabels"]
+		},
+		"parameters": {
+			"description": "Additional inference parameters",
+			"$ref": "#/$defs/ZeroShotObjectDetectionParameters"
+		}
+	},
+	"$defs": {
+		"ZeroShotObjectDetectionParameters": {
+			"title": "ZeroShotObjectDetectionParameters",
+			"description": "Additional inference parameters for Zero Shot Object Detection",
+			"type": "object",
+			"properties": {}
+		}
+	},
+	"required": ["data"]
+}

package/src/tasks/zero-shot-object-detection/spec/output.json

@@ -0,0 +1,47 @@
+{
+	"$id": "/inference/schemas/zero-shot-object-detection/output.json",
+	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Outputs of inference for the Zero Shot Object Detection task",
+	"title": "ZeroShotObjectDetectionOutput",
+	"type": "array",
+	"items": {
+		"type": "object",
+		"title": "ZeroShotObjectDetectionOutputElement",
+		"properties": {
+			"label": {
+				"type": "string",
+				"description": "A candidate label"
+			},
+			"score": {
+				"type": "number",
+				"description": "The associated score / probability"
+			},
+			"box": {
+				"$ref": "#/$defs/BoundingBox",
+				"description": "The predicted bounding box. Coordinates are relative to the top left corner of the input image."
+			}
+		},
+		"required": ["box", "label", "score"]
+	},
+	"$defs": {
+		"BoundingBox": {
+			"title": "BoundingBox",
+			"type": "object",
+			"properties": {
+				"xmin": {
+					"type": "integer"
+				},
+				"xmax": {
+					"type": "integer"
+				},
+				"ymin": {
+					"type": "integer"
+				},
+				"ymax": {
+					"type": "integer"
+				}
+			},
+			"required": ["xmin", "xmax", "ymin", "ymax"]
+		}
+	}
+}

package/tsconfig.json

@@ -2,9 +2,9 @@
 	"compilerOptions": {
 		"allowSyntheticDefaultImports": true,
 		"lib": ["ES2022", "DOM"],
-		"module": "CommonJS",
+		"module": "ESNext",
+		"target": "ESNext",
 		"moduleResolution": "node",
-		"target": "ES2022",
 		"forceConsistentCasingInFileNames": true,
 		"strict": true,
 		"noImplicitAny": true,
@@ -13,6 +13,6 @@
 		"noImplicitOverride": true,
 		"outDir": "./dist"
 	},
-	"include": ["src"],
+	"include": ["src", "scripts"],
 	"exclude": ["dist"]
 }