@huggingface/tasks 0.13.1 → 0.13.2

package/dist/esm/tasks/video-text-to-text/data.js

@@ -0,0 +1,61 @@
+const taskData = {
+    datasets: [
+        {
+            description: "Multiple-choice questions and answers about videos.",
+            id: "lmms-lab/Video-MME",
+        },
+        {
+            description: "A dataset of instructions and question-answer pairs about videos.",
+            id: "lmms-lab/VideoChatGPT",
+        },
+        {
+            description: "Large video understanding dataset.",
+            id: "HuggingFaceFV/finevideo",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "video-text-to-text-input.gif",
+                type: "img",
+            },
+            {
+                label: "Text Prompt",
+                content: "What is happening in this video?",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                label: "Answer",
+                content: "The video shows a series of images showing a fountain with water jets and a variety of colorful flowers and butterflies in the background.",
+                type: "text",
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "A robust video-text-to-text model that can take in image and video inputs.",
+            id: "llava-hf/llava-onevision-qwen2-72b-ov-hf",
+        },
+        {
+            description: "Large and powerful video-text-to-text model that can take in image and video inputs.",
+            id: "llava-hf/LLaVA-NeXT-Video-34B-hf",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application to chat with a video-text-to-text model.",
+            id: "llava-hf/video-llava",
+        },
+        {
+            description: "A leaderboard for various video-text-to-text models.",
+            id: "opencompass/openvlm_video_leaderboard",
+        },
+    ],
+    summary: "Video-text-to-text models take in a video and a text prompt and output text. These models are also called video-language models.",
+    widgetModels: [""],
+    youtubeId: "",
+};
+export default taskData;

package/dist/esm/tasks/visual-question-answering/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/visual-question-answering/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/visual-question-answering/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA4Ff,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/visual-question-answering/data.js

@@ -0,0 +1,91 @@
+const taskData = {
+    datasets: [
+        {
+            description: "A widely used dataset containing questions (with answers) about images.",
+            id: "Graphcore/vqa",
+        },
+        {
+            description: "A dataset to benchmark visual reasoning based on text in images.",
+            id: "facebook/textvqa",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "elephant.jpeg",
+                type: "img",
+            },
+            {
+                label: "Question",
+                content: "What is in this image?",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "elephant",
+                        score: 0.97,
+                    },
+                    {
+                        label: "elephants",
+                        score: 0.06,
+                    },
+                    {
+                        label: "animal",
+                        score: 0.003,
+                    },
+                ],
+            },
+        ],
+    },
+    isPlaceholder: false,
+    metrics: [
+        {
+            description: "",
+            id: "accuracy",
+        },
+        {
+            description: "Measures how much a predicted answer differs from the ground truth based on the difference in their semantic meaning.",
+            id: "wu-palmer similarity",
+        },
+    ],
+    models: [
+        {
+            description: "A visual question answering model trained to convert charts and plots to text.",
+            id: "google/deplot",
+        },
+        {
+            description: "A visual question answering model trained for mathematical reasoning and chart derendering from images.",
+            id: "google/matcha-base",
+        },
+        {
+            description: "A strong visual question answering that answers questions from book covers.",
+            id: "google/pix2struct-ocrvqa-large",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that compares visual question answering models across different tasks.",
+            id: "merve/pix2struct",
+        },
+        {
+            description: "An application that can answer questions based on images.",
+            id: "nielsr/vilt-vqa",
+        },
+        {
+            description: "An application that can caption images and answer questions about a given image. ",
+            id: "Salesforce/BLIP",
+        },
+        {
+            description: "An application that can caption images and answer questions about a given image. ",
+            id: "vumichien/Img2Prompt",
+        },
+    ],
+    summary: "Visual Question Answering is the task of answering open-ended questions based on an image. They output natural language responses to natural language questions.",
+    widgetModels: ["dandelin/vilt-b32-finetuned-vqa"],
+    youtubeId: "",
+};
+export default taskData;

package/dist/esm/tasks/visual-question-answering/inference.d.ts

@@ -0,0 +1,63 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Visual Question Answering inference
+ */
+export interface VisualQuestionAnsweringInput {
+    /**
+     * One (image, question) pair to answer
+     */
+    inputs: VisualQuestionAnsweringInputData;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: VisualQuestionAnsweringParameters;
+    [property: string]: unknown;
+}
+/**
+ * One (image, question) pair to answer
+ */
+export interface VisualQuestionAnsweringInputData {
+    /**
+     * The image.
+     */
+    image: unknown;
+    /**
+     * The question to answer based on the image.
+     */
+    question: unknown;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Visual Question Answering
+ */
+export interface VisualQuestionAnsweringParameters {
+    /**
+     * The number of answers to return (will be chosen by order of likelihood). Note that we
+     * return less than topk answers if there are not enough options available within the
+     * context.
+     */
+    top_k?: number;
+    [property: string]: unknown;
+}
+export type VisualQuestionAnsweringOutput = VisualQuestionAnsweringOutputElement[];
+/**
+ * Outputs of inference for the Visual Question Answering task
+ */
+export interface VisualQuestionAnsweringOutputElement {
+    /**
+     * The answer to the question
+     */
+    answer?: string;
+    /**
+     * The associated score / probability
+     */
+    score: number;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/visual-question-answering/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/visual-question-answering/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,4BAA4B;IAC5C;;OAEG;IACH,MAAM,EAAE,gCAAgC,CAAC;IACzC;;OAEG;IACH,UAAU,CAAC,EAAE,iCAAiC,CAAC;IAC/C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf;;OAEG;IACH,QAAQ,EAAE,OAAO,CAAC;IAClB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,iCAAiC;IACjD;;;;OAIG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,MAAM,6BAA6B,GAAG,oCAAoC,EAAE,CAAC;AACnF;;GAEG;AACH,MAAM,WAAW,oCAAoC;IACpD;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/visual-question-answering/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/zero-shot-classification/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/zero-shot-classification/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/zero-shot-classification/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAiEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/zero-shot-classification/data.js

@@ -0,0 +1,64 @@
+const taskData = {
+    datasets: [
+        {
+            description: "A widely used dataset used to benchmark multiple variants of text classification.",
+            id: "nyu-mll/glue",
+        },
+        {
+            description: "The Multi-Genre Natural Language Inference (MultiNLI) corpus is a crowd-sourced collection of 433k sentence pairs annotated with textual entailment information.",
+            id: "nyu-mll/multi_nli",
+        },
+        {
+            description: "FEVER is a publicly available dataset for fact extraction and verification against textual sources.",
+            id: "fever/fever",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                label: "Text Input",
+                content: "Dune is the best movie ever.",
+                type: "text",
+            },
+            {
+                label: "Candidate Labels",
+                content: "CINEMA, ART, MUSIC",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "CINEMA",
+                        score: 0.9,
+                    },
+                    {
+                        label: "ART",
+                        score: 0.1,
+                    },
+                    {
+                        label: "MUSIC",
+                        score: 0.0,
+                    },
+                ],
+            },
+        ],
+    },
+    metrics: [],
+    models: [
+        {
+            description: "Powerful zero-shot text classification model.",
+            id: "facebook/bart-large-mnli",
+        },
+        {
+            description: "Powerful zero-shot multilingual text classification model that can accomplish multiple tasks.",
+            id: "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
+        },
+    ],
+    spaces: [],
+    summary: "Zero-shot text classification is a task in natural language processing where a model is trained on a set of labeled examples but is then able to classify new examples from previously unseen classes.",
+    widgetModels: ["facebook/bart-large-mnli"],
+};
+export default taskData;

package/dist/esm/tasks/zero-shot-classification/inference.d.ts

@@ -0,0 +1,68 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Zero Shot Classification inference
+ */
+export interface ZeroShotClassificationInput {
+    /**
+     * The input text data, with candidate labels
+     */
+    inputs: ZeroShotClassificationInputData;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: ZeroShotClassificationParameters;
+    [property: string]: unknown;
+}
+/**
+ * The input text data, with candidate labels
+ */
+export interface ZeroShotClassificationInputData {
+    /**
+     * The set of possible class labels to classify the text into.
+     */
+    candidateLabels: string[];
+    /**
+     * The text to classify
+     */
+    text: string;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Zero Shot Classification
+ */
+export interface ZeroShotClassificationParameters {
+    /**
+     * The sentence used in conjunction with candidateLabels to attempt the text classification
+     * by replacing the placeholder with the candidate labels.
+     */
+    hypothesis_template?: string;
+    /**
+     * Whether multiple candidate labels can be true. If false, the scores are normalized such
+     * that the sum of the label likelihoods for each sequence is 1. If true, the labels are
+     * considered independent and probabilities are normalized for each candidate.
+     */
+    multi_label?: boolean;
+    [property: string]: unknown;
+}
+export type ZeroShotClassificationOutput = ZeroShotClassificationOutputElement[];
+/**
+ * Outputs of inference for the Zero Shot Classification task
+ */
+export interface ZeroShotClassificationOutputElement {
+    /**
+     * The predicted class label.
+     */
+    label: string;
+    /**
+     * The corresponding probability.
+     */
+    score: number;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/zero-shot-classification/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/zero-shot-classification/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,2BAA2B;IAC3C;;OAEG;IACH,MAAM,EAAE,+BAA+B,CAAC;IACxC;;OAEG;IACH,UAAU,CAAC,EAAE,gCAAgC,CAAC;IAC9C,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,+BAA+B;IAC/C;;OAEG;IACH,eAAe,EAAE,MAAM,EAAE,CAAC;IAC1B;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,gCAAgC;IAChD;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;;;OAIG;IACH,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,MAAM,4BAA4B,GAAG,mCAAmC,EAAE,CAAC;AACjF;;GAEG;AACH,MAAM,WAAW,mCAAmC;IACnD;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/zero-shot-classification/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/zero-shot-image-classification/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/zero-shot-image-classification/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/zero-shot-image-classification/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA+Ef,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/zero-shot-image-classification/data.js

@@ -0,0 +1,79 @@
+const taskData = {
+    datasets: [
+        {
+            // TODO write proper description
+            description: "",
+            id: "",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-classification-input.jpeg",
+                type: "img",
+            },
+            {
+                label: "Classes",
+                content: "cat, dog, bird",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                type: "chart",
+                data: [
+                    {
+                        label: "Cat",
+                        score: 0.664,
+                    },
+                    {
+                        label: "Dog",
+                        score: 0.329,
+                    },
+                    {
+                        label: "Bird",
+                        score: 0.008,
+                    },
+                ],
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "Computes the number of times the correct label appears in top K labels predicted",
+            id: "top-K accuracy",
+        },
+    ],
+    models: [
+        {
+            description: "Robust image classification model trained on publicly available image-caption data.",
+            id: "openai/clip-vit-base-patch16",
+        },
+        {
+            description: "Strong zero-shot image classification model.",
+            id: "google/siglip-so400m-patch14-224",
+        },
+        {
+            description: "Small yet powerful zero-shot image classification model that can run on edge devices.",
+            id: "apple/MobileCLIP-S1-OpenCLIP",
+        },
+        {
+            description: "Strong image classification model for biomedical domain.",
+            id: "microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application that leverages zero-shot image classification to find best captions to generate an image. ",
+            id: "pharma/CLIP-Interrogator",
+        },
+        {
+            description: "An application to compare different zero-shot image classification models. ",
+            id: "merve/compare_clip_siglip",
+        },
+    ],
+    summary: "Zero-shot image classification is the task of classifying previously unseen classes during training of a model.",
+    widgetModels: ["google/siglip-so400m-patch14-224"],
+    youtubeId: "",
+};
+export default taskData;

package/dist/esm/tasks/zero-shot-image-classification/inference.d.ts

@@ -0,0 +1,62 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Zero Shot Image Classification inference
+ */
+export interface ZeroShotImageClassificationInput {
+    /**
+     * The input image data, with candidate labels
+     */
+    inputs: ZeroShotImageClassificationInputData;
+    /**
+     * Additional inference parameters
+     */
+    parameters?: ZeroShotImageClassificationParameters;
+    [property: string]: unknown;
+}
+/**
+ * The input image data, with candidate labels
+ */
+export interface ZeroShotImageClassificationInputData {
+    /**
+     * The candidate labels for this image
+     */
+    candidateLabels: string[];
+    /**
+     * The image data to classify
+     */
+    image: unknown;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters
+ *
+ * Additional inference parameters for Zero Shot Image Classification
+ */
+export interface ZeroShotImageClassificationParameters {
+    /**
+     * The sentence used in conjunction with candidateLabels to attempt the text classification
+     * by replacing the placeholder with the candidate labels.
+     */
+    hypothesis_template?: string;
+    [property: string]: unknown;
+}
+export type ZeroShotImageClassificationOutput = ZeroShotImageClassificationOutputElement[];
+/**
+ * Outputs of inference for the Zero Shot Image Classification task
+ */
+export interface ZeroShotImageClassificationOutputElement {
+    /**
+     * The predicted class label.
+     */
+    label: string;
+    /**
+     * The corresponding probability.
+     */
+    score: number;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/zero-shot-image-classification/inference.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/zero-shot-image-classification/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;OAEG;IACH,MAAM,EAAE,oCAAoC,CAAC;IAC7C;;OAEG;IACH,UAAU,CAAC,EAAE,qCAAqC,CAAC;IACnD,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oCAAoC;IACpD;;OAEG;IACH,eAAe,EAAE,MAAM,EAAE,CAAC;IAC1B;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;;;GAIG;AACH,MAAM,WAAW,qCAAqC;IACrD;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,MAAM,iCAAiC,GAAG,wCAAwC,EAAE,CAAC;AAC3F;;GAEG;AACH,MAAM,WAAW,wCAAwC;IACxD;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/zero-shot-image-classification/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/zero-shot-object-detection/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/zero-shot-object-detection/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/zero-shot-object-detection/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA8Df,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/zero-shot-object-detection/data.js

@@ -0,0 +1,60 @@
+const taskData = {
+    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.",
+            id: "IDEA-Research/grounding-dino-base",
+        },
+        {
+            description: "Cutting-edge zero-shot object detection 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",
+        },
+        {
+            description: "A demo that combines a zero-shot object detection and mask generation model for zero-shot segmentation.",
+            id: "merve/OWLSAM",
+        },
+    ],
+    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/dist/esm/tasks/zero-shot-object-detection/inference.d.ts

@@ -0,0 +1,67 @@
+/**
+ * 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
+     */
+    inputs: 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;
+}
+//# sourceMappingURL=inference.d.ts.map