Places365 ResNet18 LiteRT fp16 (fully-GPU, Pixel 8a corr 1.0, 2ms)

.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 +1,47 @@
+---
+license: mit
+library_name: LiteRT
+pipeline_tag: image-classification
+tags: [litert, tflite, on-device, android, gpu, scene-recognition, places365, resnet]
+base_model: CSAILVision/places365
+---
+
+# Places365 ResNet18 — LiteRT (on-device scene recognition, fully-GPU)
+
+ResNet18 trained on [Places365](http://places2.csail.mit.edu/) (CSAILVision), converted to **LiteRT** and
+running **fully on the `CompiledModel` GPU** (ML Drift) on Android. **Scene/place recognition** across **365
+categories** (beach, kitchen, forest, office, restaurant, …) — a distinct task from object classification.
+
+![Places365 — image | top-5 scenes (on-device LiteRT GPU)](samples/sample.png)
+
+## On-device (Pixel 8a, Tensor G3 — verified)
+
+| | |
+|---|---|
+| nodes on GPU | **61 / 61** LITERT_CL (full residency) |
+| inference | **~2 ms** (224×224) |
+| size | 22.8 MB (fp16) |
+| accuracy | device-vs-PyTorch corr **1.0**, top-1 match |
+
+```
+image[1,3,224,224] (ImageNet-normalized) →[GPU: ResNet18]→ logits[1,365]
+```
+
+## How it converts (litert-torch) — two numerically-exact re-authorings
+
+1. global `AdaptiveAvgPool2d(1)` → `mean(3).mean(2)` (multi-axis-pool fix).
+2. **ResNet stem `MaxPool2d(3,s2,p1)` → zero-pad + valid max-pool.** PyTorch's max-pool pads with `-inf` →
+   a `PADV2` op the Mali delegate won't delegate (splits the graph → compile fail). Since the pool follows a
+   ReLU (inputs ≥ 0), a **0-pad is exactly equivalent** and emits a delegatable `PAD` → full GPU residency.
+
+Result: banned ops NONE, all tensors ≤4D, tflite-vs-torch corr **1.0**, device-vs-torch corr **1.0**.
+
+## Preprocessing
+
+Center-crop to square, resize to 224×224, /255, ImageNet mean/std, NCHW. Output 365-class scene logits;
+softmax + argmax for top-k.
+
+## License
+
+[MIT](https://github.com/CSAILVision/places365/blob/master/LICENSE). Upstream:
+[CSAILVision/places365](https://github.com/CSAILVision/places365).

places_fp16.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb6c7ee5ec21be435d6d11f24bd68e13199bb457ff4c01fb07bde213f289d39
+size 22775088