Upload CRAFT MLT 25K ONNX model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+library_name: onnx
+tags:
+  - text-detection
+  - craft
+  - onnx
+  - inference4j
+license: mit
+datasets:
+  - SynthText
+  - IC13
+  - IC17
+---
+
+# CRAFT Text Detection (MLT 25K) — ONNX
+
+ONNX export of [CRAFT](https://github.com/clovaai/CRAFT-pytorch) (Character Region Awareness for Text Detection) trained on SynthText + IC13/IC17 (MLT 25K variant).
+
+Converted for use with [inference4j](https://github.com/inference4j/inference4j), an inference-only AI library for Java.
+
+## Usage with inference4j
+
+```java
+try (Craft craft = Craft.fromPretrained("models/craft-mlt-25k")) {
+    List<TextRegion> regions = craft.detect(Path.of("document.jpg"));
+    for (TextRegion r : regions) {
+        System.out.printf("Text at [%.0f, %.0f, %.0f, %.0f] (confidence=%.2f)%n",
+            r.box().x1(), r.box().y1(), r.box().x2(), r.box().y2(),
+            r.confidence());
+    }
+}
+```
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Architecture | VGG16-BN backbone + U-Net decoder |
+| Task | Text detection (character-level region + affinity maps) |
+| Training data | SynthText + ICDAR 2013/2017 (MLT) |
+| Weights | `craft_mlt_25k.pth` from [clovaai/CRAFT-pytorch](https://github.com/clovaai/CRAFT-pytorch) |
+| ONNX opset | 17 |
+| Input | `[batch, 3, height, width]` — RGB, ImageNet-normalized, dimensions must be multiples of 32 |
+| Output: score_map | `[batch, height/2, width/2, 2]` — channel 0: region score, channel 1: affinity score |
+| Output: feature_map | `[batch, 32, height/2, width/2]` — intermediate features (optional, for refinement) |
+| Dynamic axes | Batch, height, and width are dynamic |
+
+## Preprocessing
+
+1. Resize maintaining aspect ratio (long side to target size, e.g. 1280)
+2. Round both dimensions to nearest multiple of 32
+3. ImageNet normalization: `(pixel / 255 - mean) / std`
+   - mean = `[0.485, 0.456, 0.406]`
+   - std = `[0.229, 0.224, 0.225]`
+4. NCHW layout: `[1, 3, H, W]`
+
+## Postprocessing
+
+1. Combine: `clip(region_score + affinity_score, 0, 1)`
+2. Binary threshold at `low_text_threshold` (default 0.4)
+3. Connected component labeling (4-connectivity)
+4. For each component: compute mean region score, filter by `text_threshold` (default 0.7)
+5. Extract axis-aligned bounding box, scale back to original image coordinates
+
+## Original Paper
+
+> Baek, Y., Lee, B., Han, D., Yun, S., & Lee, H. (2019).
+> Character Region Awareness for Text Detection.
+> CVPR 2019. [arXiv:1904.01941](https://arxiv.org/abs/1904.01941)
+
+## License
+
+The original CRAFT model weights are released under the MIT License by Clova AI Research (NAVER Corp).

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0773559ece3671df618d660e68782406ccfb830c18281664b453e5fe97c95bb
+size 132927

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9997d6c9b185c7eae07c338eef1a1ada086602c287b9a46dd5e6ac0c47295e
+size 83099648