Update README.md

README.md

@@ -1,11 +1,8 @@
 ---
-language: 
+language:
 - en
-
 license: mit
-
 library_name: pytorch
-
 tags:
 - computer-vision
 - image-classification
@@ -16,23 +13,16 @@ tags:
 - plants
 - environment
 - ai-for-good
-
 pipeline_tag: image-classification
-
 model_name: FloraGuard
-
 model_type: ConvNeXt-Base
-
 base_model: timm/convnext_base
-
 author: Aarav
-
 description: >
   FloraGuard is a deep learning–based image classification model designed to
   identify and classify forest and plant-related categories. It uses a
-  ConvNeXt-Base backbone pretrained on ImageNet and a custom classification
-  head for improved accuracy and generalization.
-
+  ConvNeXt-Base backbone pretrained on ImageNet and a custom classification head
+  for improved accuracy and generalization.
 training:
   framework: PyTorch
   optimizer: AdamW
@@ -41,12 +31,10 @@ training:
   epochs: 20
   scheduler: ReduceLROnPlateau
   device: CUDA / CPU
-
 architecture:
   backbone: ConvNeXt-Base (pretrained on ImageNet)
-  classification_head: >
+  classification_head: |
     Linear → BatchNorm → ReLU → Dropout → Linear
-
 dataset:
   format: ImageFolder
   structure: |
@@ -59,91 +47,68 @@ dataset:
         ├── class_1/
         ├── class_2/
         └── ...
-  description: >
+  description: |
     Multi-class forest and plant image dataset organized by class folders.
-
 augmentation:
   train:
-    - Resize (320x320)
-    - Random Horizontal Flip
-    - Random Rotation
-    - Color Jitter
-    - Normalization
+  - Resize (320x320)
+  - Random Horizontal Flip
+  - Random Rotation
+  - Color Jitter
+  - Normalization
   validation:
-    - Resize (320x320)
-    - Normalization
-
+  - Resize (320x320)
+  - Normalization
 evaluation:
   metrics:
-    - F1 Score
-    - Confusion Matrix
-    - Classification Report
-    - Training & Validation Loss Curves
-
+  - F1 Score
+  - Confusion Matrix
+  - Classification Report
+  - Training & Validation Loss Curves
 outputs:
   best_model: best_model.pth
-
 use_cases:
-  - Forest monitoring
-  - Plant classification
-  - Environmental AI applications
-  - Research and education
-
+- Forest monitoring
+- Plant classification
+- Environmental AI applications
+- Research and education
 requirements:
-  - torch
-  - torchvision
-  - timm
-  - numpy
-  - matplotlib
-  - scikit-learn
-  - pillow
+- torch
+- torchvision
+- timm
+- numpy
+- matplotlib
+- scikit-learn
+- pillow
+datasets:
+- blanchon/FireRisk
 ---
 
 
-Evaluation Results
-Classification Report
-precision  recall  f1-score  support
+###Evaluation Results
 
-High           0.31   0.43   0.36   1609
-Low            0.40   0.32   0.36   2599
-Moderate       0.20   0.16   0.17   1772
-Non-burnable   0.82   0.89   0.85   5091
-Very_High      0.36   0.54   0.43   1438
-Very_Low       0.80   0.69   0.74   8448
-Water          0.67   0.93   0.78    584
+##Classification Report & Confusion Matrix------>
 
-accuracy                0.63   21541
-macro avg      0.51   0.57   0.53   21541
-weighted avg   0.64   0.63   0.63   21541
+![image](https://cdn-uploads.huggingface.co/production/uploads/6946d101b51464b501b63953/mRic1Jb_ITOzL_79-CzAp.png)
 
-Confusion Matrix
-[[ 686   74  221   54  451  107   16]
- [ 317  842  302   76  296  733   33]
- [ 578  202  276   58  402  237   19]
- [  20   75   50 4536   37  309   64]
- [ 358   45  213    5  783   30    4]
- [ 282  877  329  786  213 5829  132]
- [   7    7    1    8    2   15  544]]
 
-Notes
+###Notes
 
-Overall accuracy: 0.63
+-Overall accuracy: 0.63 or 63%
 
-Best performing classes:
+-Best performing classes:
 
-Non-burnable (F1: 0.85)
+-----Non-burnable (F1: 0.85)
 
-Very_Low (F1: 0.74)
+-----Very_Low (F1: 0.74)
 
-Water (F1: 0.78)
+-----Water (F1: 0.78)
 
-Weaker performance on:
+-Weaker performance on:
 
-Moderate
+-----Moderate
 
-High
+-----High
 
-Low
+-----Low
 
-**DISCLOSURES**
--Model was developed with assistance from Github Copilot Only for the augmentation techniques. (MIXUP, CUTMIX)