Add model

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+datasets:
+- ILSVRC/imagenet-1k
+metrics:
+- accuracy
+language:
+- en
+tags:
+- vision
+- image-classification
+- pytorch_model_hub_mixin
+pipeline_tag: image-classification
+library_name: PyTorch
+model_index:
+- name: SpaRTAN-S
+  results:
+  - task:
+      type: image-classification
+    dataset:
+      type: ILSVRC/imagenet-1k
+      name: ImageNet-1k
+    metrics:
+    - name: top-1 accuracy
+      type: accuracy
+      value: 82.35
+    - name: top-5 accuracy
+      type: accuracy
+      value: 96.14
+---
+
+# SpaRTAN-S
+
+SpaRTAN is a lightweight architectural design which shows consistent efficiency and competitive performance when benchmarked against ImageNet and COCO dataset. It was introduced in the paper [SpaRTAN](https://arxiv.org/abs/2507.10999) and released in this [repo](https://github.com/henry-pay/SpaRTAN). SpaRTAN-S is a scaled-up version of SpaRTAN-T.
+
+# Model Description
+
+SpaRTAN-S shares the same configurations as SpaRTAN-T presented in the paper, [SpaRTAN](https://arxiv.org/abs/2507.10999), except the number of channels at each stage, as outlined below.
+
+| Stage | Channel |
+|:---:|:---:|
+| S1 | 64 |
+| S2 | 128 |
+| S3 | 320 |
+| S4 | 512 |
+
+# Intended Uses & Limitations
+
+You can use the raw model for image classification. Using as a feature extractor, SpaRTAN-S can be fine-tuned on various downstream tasks including object detection.
+
+# Training Procedure
+
+Same training procedure as outlined in the paper, [SpaRTAN](https://arxiv.org/abs/2507.10999), is used to train this model.
+
+# Evaluation Result
+
+| Model | Resolution | Params (M) | FLOPs (G) | Top-1 (%) | top-5 (%) |
+|:---:|:---:|:---:|:---:|:---:|:---:|
+| SpaRTAN-S | 224x224 | 18.51 | 3.86 | 82.35 | 96.14 |
+
+# Implementation
+
+Please refer to this [repo](https://github.com/henry-pay/SpaRTAN) for full implementation.
+
+# Citation
+
+```bibtex
+@inproceedings{
+    title={SpaRTAN: Spatial Reinforcement Token-based Aggregation Network for Visual Recognition},
+    author={Pay, Quan Bi and Baskaran, Vishnu Monn and Loo, Junn Yong and Wong, KokSheik and See, Simon},
+    booktitle={2025 International Joint Conference on Neural Networks (IJCNN)},
+    pages={to appear},
+    year={2025},
+    organization={IEEE},
+    note={Accepted}
+}
+```

config.json

@@ -0,0 +1,23 @@
+{
+  "dims": [
+    128,
+    320,
+    512
+  ],
+  "dropout": 0.1,
+  "expand_ratios": [
+    4,
+    4,
+    2,
+    2
+  ],
+  "init_dim": 64,
+  "layer_depths": [
+    3,
+    3,
+    12,
+    2
+  ],
+  "num_classes": 1000,
+  "num_layer": 4
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834c5949b4472448006e3a8500953f0df1ab8dd8ec7653214f0044e4e4fe9e14
+size 74291312