Upload README.md with huggingface_hub

README.md

@@ -22,7 +22,7 @@ pipeline_tag: image-segmentation
 3m PlanetScope field-boundary segmentation model from **Fields of the Planet
 (FTP)**, a PlanetScope companion to [Fields of the World
 (FTW)](https://github.com/fieldsoftheworld/ftw-baselines). Larger-backbone
-variant of the paper's headline model ([`ftp-b3`](https://huggingface.co/taylor-geospatial/ftp-b3)).
+variant of the paper's main reported model ([`ftp-b3`](https://huggingface.co/taylor-geospatial/ftp-b3)).
 
 U-Net decoder over an EfficientNet-B7 encoder, trained on paired planting-
 and harvest-window PlanetScope surface-reflectance imagery (8 input
@@ -59,8 +59,8 @@ logits = model(image)  # image: (B, 8, H, W) float32, 2 seasonal windows x 4 ban
 
 ### Lightning checkpoint (raw `smp.Unet`)
 
-The checkpoint's `state_dict` is just an `smp.Unet` under a `model.` prefix —
-unless you need the Lightning training wrapper, `smp.from_pretrained` above
+The checkpoint's `state_dict` is just an `smp.Unet` under a `model.` prefix.
+Unless you need the Lightning training wrapper, `smp.from_pretrained` above
 is simpler.
 
 ```python
@@ -95,7 +95,7 @@ model = exported.module()
 logits = model(image)  # image: (B, 8, 512, 512) float32, any batch size
 ```
 
-Output is 3-class logits (background / field / boundary); argmax + the
+Output is 3-class logits (background / field / boundary). Argmax plus the
 repo's watershed post-processing (`scripts/eval/postprocess_eval.py`)
 recovers instance polygons.
 
@@ -121,9 +121,9 @@ confidence setting. † Pixel IoU is not comparable across sensors due to
 differences in resolution. ‡ PQ for small (<0.5 ha), medium (0.5-2 ha), and
 large (>2 ha) ground-truth fields.
 
-The B3 variant scores marginally higher PQ (35.5 vs 35.4) at ~5x fewer
-parameters; B7 trades that for better pixel IoU (74.2 vs 68.8) and
-medium-field PQ (40.6 vs 39.2).
+The B3 variant scores higher PQ (35.5 vs 35.4) at about 5x fewer parameters,
+but B7 has better pixel IoU (74.2 vs 68.8) and medium-field PQ (40.6 vs
+39.2).
 
 ## Citation