NAFNet-SIDD-width32 LiteRT fp16 (fully-GPU denoise, Pixel 8a corr 1.0)

.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
+samples/sample.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+library_name: LiteRT
+pipeline_tag: image-to-image
+tags:
+  - litert
+  - tflite
+  - on-device
+  - android
+  - gpu
+  - image-restoration
+  - denoising
+  - nafnet
+base_model: megvii-research/NAFNet
+---
+
+# NAFNet-SIDD-width32 — LiteRT (on-device image denoising, fully-GPU)
+
+[NAFNet](https://github.com/megvii-research/NAFNet) (Nonlinear Activation Free Network, ECCV 2022) image
+restoration, converted to **LiteRT** and running **fully on the `CompiledModel` GPU** (ML Drift) on Android.
+This is the **SIDD-width32** variant — real-image **denoising**. NAFNet is a U-Net of NAFBlocks with **no
+activation functions** (SimpleGate = channel-split multiply), so the whole network is a clean CNN on the GPU.
+
+![NAFNet-SIDD — noisy input | denoised (on-device LiteRT GPU)](samples/sample.png)
+
+## On-device (Pixel 8a, Tensor G3 — verified)
+
+| | |
+|---|---|
+| nodes on GPU | **2179 / 2179** LITERT_CL (full residency) |
+| inference | **~46 ms** (256×256) |
+| size | 62.5 MB (fp16) |
+| accuracy | device output **== PyTorch (corr 0.999999)** — re-authoring is numerically exact |
+
+```
+image[1,3,256,256] (RGB [0,1]) →[GPU: NAFNet U-Net]→ denoised[1,3,256,256]
+```
+
+## How it converts (litert-torch)
+
+Pure CNN (no activations). Three numerically-exact re-authorings, the headline being **SafeLayerNorm**:
+NAFNet's residual stream grows large (|x|≈175 at the bottleneck), so the LayerNorm channel reductions
+`Σ_c x` and `Σ_c (x−μ)²` (~15M) **overflow fp16 (max 65504)** on the Mali delegate (which computes in fp16
+regardless of the model dtype) → a grid artifact. Doing the reductions in a down-scaled `x/S` domain (S=128)
+and rescaling is exact and fp16-safe. Plus the Simplified Channel Attention `AdaptiveAvgPool2d(1)` →
+`mean(3).mean(2)`, and the upsample `Conv2d(1×1)+PixelShuffle(2)` → depth-to-space `ZeroStuffConvT2d`.
+
+Result: banned ops NONE, all tensors ≤4D, tflite-vs-torch corr **1.0**, device-vs-torch corr **1.0**.
+
+A complete Android sample (image picker + before/after) is in the official
+[google-ai-edge/litert-samples](https://github.com/google-ai-edge/litert-samples) repo under
+`compiled_model_api/image_restoration` (push this `.tflite` in place of the deblur model).
+
+## License
+
+[MIT](https://github.com/megvii-research/NAFNet/blob/main/LICENSE). Upstream:
+[megvii-research/NAFNet](https://github.com/megvii-research/NAFNet); weights NAFNet-SIDD-width32.

nafnet_sidd_width32_fp16.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8fbaa422411683c53e802cf7cc7cf9be0a0de00886ad4af057232e26b172a0c
+size 62454048