Upload README.md with huggingface_hub

README.md

@@ -1,26 +1,63 @@
 ---
+license: mit
 tags:
-- ml-intern
+- pointnet
+- modelnet40
+- 3d-classification
+- point-cloud
+- pytorch
+metrics:
+- accuracy
+model-index:
+- name: pointnet-modelnet40
+  results:
+  - task:
+      type: 3d-shape-classification
+    dataset:
+      type: modelnet40
+      name: ModelNet40
+    metrics:
+    - type: accuracy
+      value: 83.83
 ---
 
-# DavidHanSZ/pointnet-modelnet40
+# PointNet for ModelNet40 Classification
 
-<!-- ml-intern-provenance -->
-## Generated by ML Intern
+Reimplementation of [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://arxiv.org/abs/1612.00593) (Qi et al., 2017).
 
-This model repository was generated by [ML Intern](https://github.com/huggingface/ml-intern), an agent for machine learning research and development on the Hugging Face Hub.
+## Architecture
 
-- Try ML Intern: https://smolagents-ml-intern.hf.space
-- Source code: https://github.com/huggingface/ml-intern
+Exact architecture from the paper (Appendix C):
+- Input Transform (T-Net 3×3): MLP(64,128,1024) → max pool → FC(512,256) → 3×3
+- Shared MLP(64,64) → Feature Transform (T-Net 64×64) → MLP(64,128,1024)
+- Global max pool → FC(512,256,40) + dropout(0.3)
+- Orthogonal regularization (λ=0.001) on both T-Nets
+
+## Training Recipe (from paper)
+
+| Parameter | Value |
+|-----------|-------|
+| Points sampled | 1024 (uniform, normalized to unit sphere) |
+| Augmentation | Random up-axis rotation + Gaussian jitter (σ=0.02) |
+| Optimizer | Adam, lr=0.001, β₁=0.9 |
+| Batch size | 32 |
+| LR schedule | ÷2 every 20 epochs |
+| Epochs trained | 250 |
+| Best test accuracy | **83.83%** (epoch 238) |
 
 ## Usage
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_id = "DavidHanSZ/pointnet-modelnet40"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+import torch
+# Copy the PointNetClassification class from pointnet_modelnet40.py
+model = PointNetClassification(num_classes=40)
+model.load_state_dict(torch.load('pytorch_model.bin'))
+model.eval()
+
+# Input: (B, 3, 1024) point cloud normalized to unit sphere
+# Output: (B, 40) logits
 ```
 
-For non-causal architectures, replace `AutoModelForCausalLM` with the appropriate `AutoModel` class.
+## Dataset
+
+Trained on [jxie/modelnet40-2048](https://huggingface.co/datasets/jxie/modelnet40-2048) — 9,840 train / 2,468 test samples across 40 object categories.