rotsl commited on
Commit
bcfdee2
Β·
verified Β·
1 Parent(s): 073d55f

Add both demo Spaces with accuracy comparison

Browse files
Files changed (1) hide show
  1. README.md +8 -4
README.md CHANGED
@@ -31,7 +31,7 @@ PyTorch U-Net models for **gray leaf spot** (*Magnaporthe* and related fungal) c
31
  | `best_area_w_0.1.pt` | SmallUNet | ~250 K | 0.1 | Light area regularisation |
32
  | `best_area_w_0.3.pt` | SmallUNet | ~250 K | 0.3 | Moderate area regularisation |
33
  | `best_area_w_0.5.pt` | SmallUNet | ~250 K | 0.5 | Balanced BCE + area |
34
- | **`best_area_w_0.7.pt`** | **SmallUNet** | **~250 K** | **0.7** | **Strong area consistency (used by demo)** |
35
 
36
  All SmallUNet variants share the same architecture:
37
 
@@ -173,16 +173,20 @@ python src/predict.py --input raw --weights models/best_finetuned.pt --output-di
173
 
174
  ---
175
 
176
- ## Demo Space
177
 
178
- The full analysis pipeline is available as a Gradio Space:
179
 
180
- **[`rotsl/grayleafspot-segmentation-demo`](https://huggingface.co/spaces/rotsl/grayleafspot-segmentation-demo)**
181
 
182
  Features: dish detection β†’ colony segmentation β†’ crack & hyphae analysis β†’ 16 morphometric measurements β†’ time-series growth charts β†’ CSV/JSON export.
183
 
184
  Source code: [`rotsl/grayleafspot-segmentation-demo`](https://huggingface.co/rotsl/grayleafspot-segmentation-demo) (model repo)
185
 
 
 
 
 
186
  ---
187
 
188
  ## Citation
 
31
  | `best_area_w_0.1.pt` | SmallUNet | ~250 K | 0.1 | Light area regularisation |
32
  | `best_area_w_0.3.pt` | SmallUNet | ~250 K | 0.3 | Moderate area regularisation |
33
  | `best_area_w_0.5.pt` | SmallUNet | ~250 K | 0.5 | Balanced BCE + area |
34
+ | **`best_area_w_0.7.pt`** | **SmallUNet** | **~250 K** | **0.7** | **Strong area consistency (used by demo) βœ… recommended** |
35
 
36
  All SmallUNet variants share the same architecture:
37
 
 
173
 
174
  ---
175
 
176
+ ## Demo Spaces
177
 
178
+ ### βœ… Recommended: [`rotsl/grayleafspot-segmentation-demo`](https://huggingface.co/spaces/rotsl/grayleafspot-segmentation-demo)
179
 
180
+ Uses **`best_area_w_0.7.pt`** (SmallUNet with area-consistency loss). More accurate segmentation with better boundary adherence thanks to the area-consistency regularisation.
181
 
182
  Features: dish detection β†’ colony segmentation β†’ crack & hyphae analysis β†’ 16 morphometric measurements β†’ time-series growth charts β†’ CSV/JSON export.
183
 
184
  Source code: [`rotsl/grayleafspot-segmentation-demo`](https://huggingface.co/rotsl/grayleafspot-segmentation-demo) (model repo)
185
 
186
+ ### Legacy: [`rotsl/fungal-colony-input`](https://huggingface.co/spaces/rotsl/fungal-colony-input)
187
+
188
+ Uses **`grayleafspot.pt`** (smp.Unet with ResNet-34 encoder). This is the earlier, larger model trained with standard BCE loss only β€” it is less accurate than the area-consistency variant above, particularly for colony boundary delineation and area estimation. Kept available for reference and backward compatibility.
189
+
190
  ---
191
 
192
  ## Citation