Add LiteRT TIMM regnetx_032.tv2_in1k

README.md

@@ -0,0 +1,90 @@
+---
+library_name: litert
+base_model: timm/regnetx_032.tv2_in1k
+pipeline_tag: image-classification
+tags:
+  - tflite
+  - vision
+  - image-classification
+  - google
+  - computer-vision
+datasets:
+  - imagenet-1k
+---
+
+# Regnetx 032
+
+This repository contains LiteRT/TFLite exports of the TIMM image-classification model `regnetx_032.tv2_in1k`.
+
+## Model Description
+
+The model files were converted from pretrained TIMM weights published at `timm/regnetx_032.tv2_in1k`.
+
+## Available Model Files
+
+| File | Description | Quantization |
+|---|---|---|
+| `regnetx_032_fp32.tflite` | Floating-point LiteRT/TFLite model. | Floating-point weights and activations. |
+| `regnetx_032_dynamic_wi8_afp32.tflite` | Dynamic weight-quantized LiteRT/TFLite model. | INT8 weights with floating-point activations. |
+| `regnetx_032_int8_channelwise.tflite` | Static INT8 LiteRT/TFLite model. | INT8 weights and INT8 activations, with channelwise weight quantization. |
+
+## Quantization Schema
+
+`regnetx_032_int8_channelwise.tflite` was quantized with AI Edge Quantizer's static W8A8 recipe (`STATIC_WI8_AI8`).
+
+The schema is:
+
+| Tensor group | Quantization |
+|---|---|
+| Weights | INT8, symmetric, channelwise quantization. |
+| Activations | INT8, asymmetric, tensorwise quantization. |
+| Model input | INT8, tensorwise quantized NCHW image tensor with shape `[1, 3, 224, 224]`. |
+| Model output | INT8, tensorwise quantized logits tensor with shape `[1, 1000]`. |
+
+Calibration used real ImageNet validation images with the TIMM preprocessing flow for `regnetx_032.tv2_in1k`. The resolved TIMM preprocessing config was `{"crop_mode": "center", "crop_pct": 0.965, "input_size": [3, 224, 224], "interpolation": "bicubic", "mean": [0.485, 0.456, 0.406], "std": [0.229, 0.224, 0.225]}`. When using APIs that expose raw tensor buffers, prepare the input and output using the quantization parameters stored in the model.
+
+## Runtime Compatibility
+
+These artifacts are intended for LiteRT CPU and GPU execution.
+
+The static INT8 channelwise artifact also AOT-compiled successfully through the LiteRT Qualcomm compiler plugin for SM8750, with the compiled model fully selected into Qualcomm NPU dispatch.
+
+MediaTek NPU enablement for the static INT8 channelwise artifact is still under validation. LiteRT AOT compilation for mt6993 did not complete in this release run, so this repository does not mark that artifact as MediaTek-NPU-ready yet.
+
+## Intended Uses & Limitations
+
+The model files were converted from pretrained weights from TIMM. The models may have their own licenses or terms and conditions derived from TIMM and the dataset used for training. It is your responsibility to determine whether you have permission to use the models for your use case.
+
+## Model Details
+
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 15.3
+  - GMACs: 3.2
+  - Activations (M): 11.4
+  - Image size: 224 x 224
+- **Papers:**
+  - Designing Network Design Spaces: https://arxiv.org/abs/2003.13678
+- **Original:** https://github.com/pytorch/vision
+
+## Citation
+
+```bibtex
+@InProceedings{Radosavovic2020,
+  title = {Designing Network Design Spaces},
+  author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{'a}r},
+  booktitle = {CVPR},
+  year = {2020}
+}
+```
+```bibtex
+@misc{rw2019timm,
+  author = {Ross Wightman},
+  title = {PyTorch Image Models},
+  year = {2019},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  doi = {10.5281/zenodo.4414861},
+  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
+}
+```

regnetx_032_dynamic_wi8_afp32.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578df753f0d9df296db811ca1acd42563bbb7d82b1c9e61ea1c8097dbe84bece
+size 15963840

regnetx_032_fp32.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90817699f2f025165b247525e329d450f2b294ba9bfa346bddd8fef5f32a1966
+size 61257360

regnetx_032_int8_channelwise.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40544aff44244ff6577021690d5fe5596c4375c1f386988f345d31deb9d2642
+size 16381728