Add support for TextNet

README.md

@@ -407,6 +407,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **[T5](https://huggingface.co/docs/transformers/model_doc/t5)** (from Google AI) released with the paper [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/abs/1910.10683) by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
 1. **[T5v1.1](https://huggingface.co/docs/transformers/model_doc/t5v1.1)** (from Google AI) released in the repository [google-research/text-to-text-transfer-transformer](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/released_checkpoints.md#t511) by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
 1. **[Table Transformer](https://huggingface.co/docs/transformers/model_doc/table-transformer)** (from Microsoft Research) released with the paper [PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents](https://arxiv.org/abs/2110.00061) by Brandon Smock, Rohith Pesala, Robin Abraham.
+1. **[TextNet](https://huggingface.co/docs/transformers/model_doc/textnet)** released with the paper [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://arxiv.org/abs/2111.02394) by Zhe Chen, Jiahao Wang, Wenhai Wang, Guo Chen, Enze Xie, Ping Luo, Tong Lu.
 1. **[TrOCR](https://huggingface.co/docs/transformers/model_doc/trocr)** (from Microsoft), released together with the paper [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282) by Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei.
 1. **[UniSpeech](https://huggingface.co/docs/transformers/model_doc/unispeech)** (from Microsoft Research) released with the paper [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://arxiv.org/abs/2101.07597) by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang.
 1. **[UniSpeechSat](https://huggingface.co/docs/transformers/model_doc/unispeech-sat)** (from Microsoft Research) released with the paper [UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING](https://arxiv.org/abs/2110.05752) by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu.

docs/snippets/6_supported-models.snippet

@@ -122,6 +122,7 @@
 1. **[T5](https://huggingface.co/docs/transformers/model_doc/t5)** (from Google AI) released with the paper [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/abs/1910.10683) by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
 1. **[T5v1.1](https://huggingface.co/docs/transformers/model_doc/t5v1.1)** (from Google AI) released in the repository [google-research/text-to-text-transfer-transformer](https://github.com/google-research/text-to-text-transfer-transformer/blob/main/released_checkpoints.md#t511) by Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu.
 1. **[Table Transformer](https://huggingface.co/docs/transformers/model_doc/table-transformer)** (from Microsoft Research) released with the paper [PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents](https://arxiv.org/abs/2110.00061) by Brandon Smock, Rohith Pesala, Robin Abraham.
+1. **[TextNet](https://huggingface.co/docs/transformers/model_doc/textnet)** released with the paper [FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation](https://arxiv.org/abs/2111.02394) by Zhe Chen, Jiahao Wang, Wenhai Wang, Guo Chen, Enze Xie, Ping Luo, Tong Lu.
 1. **[TrOCR](https://huggingface.co/docs/transformers/model_doc/trocr)** (from Microsoft), released together with the paper [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282) by Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei.
 1. **[UniSpeech](https://huggingface.co/docs/transformers/model_doc/unispeech)** (from Microsoft Research) released with the paper [UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data](https://arxiv.org/abs/2101.07597) by Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang.
 1. **[UniSpeechSat](https://huggingface.co/docs/transformers/model_doc/unispeech-sat)** (from Microsoft Research) released with the paper [UNISPEECH-SAT: UNIVERSAL SPEECH REPRESENTATION LEARNING WITH SPEAKER AWARE PRE-TRAINING](https://arxiv.org/abs/2110.05752) by Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu.

src/models.js

@@ -4712,6 +4712,18 @@ export class ViTForImageClassification extends ViTPreTrainedModel {
 }
 //////////////////////////////////////////////////
 
+//////////////////////////////////////////////////
+export class TextNetPreTrainedModel extends PreTrainedModel { }
+export class TextNetModel extends TextNetPreTrainedModel { }
+export class TextNetForImageClassification extends TextNetPreTrainedModel {
+    /**
+     * @param {any} model_inputs
+     */
+    async _call(model_inputs) {
+        return new SequenceClassifierOutput(await super._call(model_inputs));
+    }
+}
+//////////////////////////////////////////////////
 
 //////////////////////////////////////////////////
 export class IJepaPreTrainedModel extends PreTrainedModel { }
@@ -7002,6 +7014,7 @@ const MODEL_MAPPING_NAMES_ENCODER_ONLY = new Map([
     ['rt_detr', ['RTDetrModel', RTDetrModel]],
     ['table-transformer', ['TableTransformerModel', TableTransformerModel]],
     ['vit', ['ViTModel', ViTModel]],
+    ['textnet', ['TextNetModel', TextNetModel]],
     ['ijepa', ['IJepaModel', IJepaModel]],
     ['pvt', ['PvtModel', PvtModel]],
     ['vit_msn', ['ViTMSNModel', ViTMSNModel]],
@@ -7251,6 +7264,7 @@ const MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES = new Map([
 
 const MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES = new Map([
     ['vit', ['ViTForImageClassification', ViTForImageClassification]],
+    ['textnet', ['TextNetForImageClassification', TextNetForImageClassification]],
     ['ijepa', ['IJepaForImageClassification', IJepaForImageClassification]],
     ['pvt', ['PvtForImageClassification', PvtForImageClassification]],
     ['vit_msn', ['ViTMSNForImageClassification', ViTMSNForImageClassification]],

src/models/image_processors.js

@@ -32,6 +32,7 @@ export * from './sam/image_processing_sam.js'
 export * from './segformer/image_processing_segformer.js'
 export * from './siglip/image_processing_siglip.js'
 export * from './swin2sr/image_processing_swin2sr.js'
+export * from './textnet/image_processing_textnet.js'
 export * from './vit/image_processing_vit.js'
 export * from './vitmatte/image_processing_vitmatte.js'
 export * from './vitpose/image_processing_vitpose.js'

src/models/textnet/image_processing_textnet.js

@@ -0,0 +1,6 @@
+import { 
+    ImageProcessor,
+} from "../../base/image_processors_utils.js";
+
+export class TextNetImageProcessor extends ImageProcessor { }
+

tests/models/textnet/test_image_processing_textnet.js

@@ -0,0 +1,31 @@
+import { AutoImageProcessor, TextNetImageProcessor } from "../../../src/transformers.js";
+
+import { load_cached_image } from "../../asset_cache.js";
+import { MAX_PROCESSOR_LOAD_TIME, MAX_TEST_EXECUTION_TIME } from "../../init.js";
+
+export default () => {
+  describe("TextNetImageProcessor", () => {
+    const model_id = "onnx-community/textnet-tiny";
+
+    /** @type {TextNetImageProcessor} */
+    let processor;
+    beforeAll(async () => {
+      processor = await AutoImageProcessor.from_pretrained(model_id);
+    }, MAX_PROCESSOR_LOAD_TIME);
+
+    it(
+      "default",
+      async () => {
+        const image = await load_cached_image("receipt");
+        const { pixel_values, original_sizes, reshaped_input_sizes } = await processor(image);
+
+        expect(pixel_values.dims).toEqual([1, 3, 960, 640]);
+        expect(pixel_values.mean().item()).toBeCloseTo(0.8106788992881775, 6);
+
+        expect(original_sizes).toEqual([[864, 576]]);
+        expect(reshaped_input_sizes).toEqual([[960, 640]]);
+      },
+      MAX_TEST_EXECUTION_TIME,
+    );
+  });
+};