reorg app. add description

app.py

@@ -12,12 +12,18 @@ example_images = sorted(glob.glob('examples/map*.jpg'))
 ade_mean=[0.485, 0.456, 0.406]
 ade_std=[0.229, 0.224, 0.225]
 
+test_transform = T.Compose([
+    T.ToTensor(),
+    T.Normalize(mean=ade_mean, std=ade_std)
+])
+
 palette = [
     [120, 120, 120], [4, 200, 4], [4, 4, 250], [6, 230, 230],
     [80, 50, 50], [120, 120, 80], [140, 140, 140], [204, 5, 255]
 ]
 
 model_id = f"thiagohersan/maskformer-satellite-trees"
+vegetation_labels = ["vegetation"]
 
 # preprocessor = MaskFormerImageProcessor.from_pretrained(model_id)
 preprocessor = MaskFormerImageProcessor(
@@ -31,16 +37,11 @@ preprocessor = MaskFormerImageProcessor(
 hf_token = environ.get('HFTOKEN')
 model = MaskFormerForInstanceSegmentation.from_pretrained(model_id, use_auth_token=hf_token)
 
-test_transform = T.Compose([
-    T.ToTensor(),
-    T.Normalize(mean=ade_mean, std=ade_std)
-])
 
-def visualize_instance_seg_mask(img_in, mask, id2label):
+def visualize_instance_seg_mask(img_in, mask, id2label, included_labels):
     img_out = np.zeros((mask.shape[0], mask.shape[1], 3))
     image_total_pixels = mask.shape[0] * mask.shape[1]
     label_ids = np.unique(mask)
-    vegetation_labels = ["vegetation"]
 
     id2color = {id: palette[id] for id in label_ids}
     id2count = {id: 0 for id in label_ids}
@@ -56,7 +57,7 @@ def visualize_instance_seg_mask(img_in, mask, id2label):
         f"{id2label[id]}",
         f"{(100 * id2count[id] / image_total_pixels):.2f} %",
         f"{np.sqrt(id2count[id] / image_total_pixels):.2f} m"
-        ] for id in label_ids if id2label[id] in vegetation_labels]
+        ] for id in label_ids if id2label[id] in included_labels]
 
     if len(dataframe) < 1:
         dataframe = [[
@@ -72,27 +73,28 @@ def query_image(image_path):
     img = np.array(Image.open(image_path))
     img_size = (img.shape[0], img.shape[1])
     inputs = preprocessor(images=test_transform(img), return_tensors="pt")
-
     outputs = model(**inputs)
-
     results = preprocessor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[img_size])[0]
-    mask_img, dataframe = visualize_instance_seg_mask(img, results.numpy(), model.config.id2label)
+    mask_img, dataframe = visualize_instance_seg_mask(img, results.numpy(), model.config.id2label, vegetation_labels)
     return mask_img, dataframe
 
 
 demo = gr.Interface(
+    title="Maskformer Satellite+Trees",
+    description="Using a finetuned version of the [facebook/maskformer-swin-base-ade](https://huggingface.co/facebook/maskformer-swin-base-ade) model (created specifically to work with satellite images) to calculate percentage of pixels in an image that belong to vegetation.",
+
     fn=query_image,
     inputs=[gr.Image(type="filepath", label="Input Image")],
     outputs=[
         gr.Image(label="Vegetation"),
         gr.DataFrame(label="Info", headers=["Object Label", "Pixel Percent", "Square Length"])
     ],
-    title="Maskformer Satellite+Trees",
-    allow_flagging="never",
-    analytics_enabled=None,
+
     examples=example_images,
-    cache_examples=True
+    cache_examples=True,
+
+    allow_flagging="never",
+    analytics_enabled=None
 )
 
-demo.queue(concurrency_count=4, max_size=1)
 demo.launch(show_api=False)