---
license: apache-2.0
library_name: timm
tags:
  - image-classification
  - plant-disease
  - dinov2
  - rocm
  - mi300x
  - amd
base_model: facebook/dinov2-large
datasets:
  - mendeley/crop-pest-and-disease-detection
---

# DINOv2-Large — CCMT Crop & Disease (MI300X fine-tune)

Fine-tuned **DINOv2-Large** (304M params) on the **CCMT crop-pest-and-disease** dataset
(22 classes across cashew, cassava, maize, tomato).

Trained on a single **AMD Instinct MI300X** using PyTorch + ROCm, as a submission to the
lablab.ai AMD hackathon **Track 2 — Fine-Tuning on AMD GPUs**.

## 🌱 Try the live demo

This model is deployed as an interactive Gradio Space — upload a leaf photo and get an instant diagnosis with treatment guidance:

**👉 [https://huggingface.co/spaces/iamcode6/merolav-space](https://huggingface.co/spaces/iamcode6/merolav-space)**

## Results

| Metric              | This model (DINOv2-L / MI300X) | Baseline (EfficientNetB0 / P100) |
|---------------------|-------------------------------:|---------------------------------:|
| Test accuracy       | 0.9706 (TTA) | 0.9316 (TTA) |
| Macro F1            | 0.9713  | 0.9348 |
| Standard acc (no TTA) | 0.9705     | — |

TTA rounds: 10.

## Training

- **Backbone:** DINOv2-L ViT-L/14 (self-supervised, LVD-142M pretrain)
- **Precision:** bf16 (native MI300X)
- **Schedule:** 2-phase — linear probe → full fine-tune with layer-wise LR decay
- **Optimizer:** AdamW, cosine schedule, grad-clip 1.0
- **Augmentation:** RandAugment + Mixup/CutMix + RandomErasing

See `config.yaml` for the full hyperparameter set.

## Usage

```python
import timm, torch

model = timm.create_model(
    "vit_large_patch14_dinov2.lvd142m",
    pretrained=False,
    num_classes=22,
    img_size=224,
)
ckpt = torch.load("best.pt", map_location="cpu", weights_only=False)
model.load_state_dict(ckpt["state_dict"])
model.eval()
```

Class index map is embedded inside the checkpoint under `cfg`; see the training repo
for `splits.json` which defines the `class_to_idx` mapping.

## Artifacts

- `best.pt` — model weights + training config
- `config.yaml` — hyperparameters used for this run
- `classification_report.txt` — per-class precision / recall / F1
- `confusion_matrix.csv` — 22×22 confusion matrix
- `metrics.json` — standard + TTA scores

## Source

Training code: <https://github.com/genyarko/amd-merolav/tree/main/track2_finetuning>