app.py

import gradio as gr
import numpy as np
from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation


# feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-tiny-coco")
# model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-tiny-coco")
feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-large-coco")
model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-large-coco")

def visualize_instance_seg_mask(img_in, mask, id2label):
 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 = ["tree-merged", "grass-merged"]

 def get_color(id):
 id_color = (np.random.randint(0, 2), np.random.randint(0, 4), np.random.randint(0, 256))
 if id2label[id] in vegetation_labels:
 id_color = (0, 140, 0)
 return id_color

 id2color = {id: get_color(id) for id in label_ids}
 id2count = {id: 0 for id in label_ids}

 for i in range(img_out.shape[0]):
 for j in range(img_out.shape[1]):
 img_out[i, j, :] = id2color[mask[i, j]]
 id2count[mask[i, j]] = id2count[mask[i, j]] + 1

 image_res = (0.5 * img_in + 0.5 * img_out) / 255

 vegetation_count = sum([id2count[id] for id in label_ids if id2label[id] in vegetation_labels])

 dataframe_vegetation_items = [[
 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]
 dataframe_all_items = [[
 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]
 dataframe_vegetation_total = [[
 f"vegetation",
 f"{(100 * vegetation_count / image_total_pixels):.2f} %",
 f"{np.sqrt(vegetation_count / image_total_pixels):.2f} m"]]

 return image_res, dataframe_vegetation_total


def query_image(img):
 img_size = (img.shape[0], img.shape[1])
 inputs = feature_extractor(images=img, return_tensors="pt")
 outputs = model(**inputs)
 results = feature_extractor.post_process_semantic_segmentation(outputs=outputs, target_sizes=[img_size])[0]
 results = visualize_instance_seg_mask(img, results.numpy(), model.config.id2label)
 return results


demo = gr.Interface(
 query_image,
 inputs=[gr.Image(label="Input Image")],
 outputs=[
 gr.Image(label="Vegetation"),
 gr.DataFrame(label="Info", headers=["Object Label", "Pixel Percent", "Square Length"])
 ],
 title="Maskformer (large-coco)",
 allow_flagging="never",
 analytics_enabled=None
)

demo.launch(show_api=False)