Create app.py

app.py

@@ -0,0 +1,28 @@
+from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation
+from PIL import Image
+import requests
+import torch
+
+# Load Mask2Former trained on COCO instance segmentation dataset
+image_processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-small-coco-instance")
+model = Mask2FormerForUniversalSegmentation.from_pretrained(
+    "facebook/mask2former-swin-small-coco-instance"
+)
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+inputs = image_processor(image, return_tensors="pt")
+
+with torch.no_grad():
+    outputs = model(**inputs)
+
+# Model predicts class_queries_logits of shape `(batch_size, num_queries)`
+# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
+class_queries_logits = outputs.class_queries_logits
+masks_queries_logits = outputs.masks_queries_logits
+
+# Perform post-processing to get instance segmentation map
+pred_instance_map = image_processor.post_process_semantic_segmentation(
+    outputs, target_sizes=[image.size[::-1]]
+)[0]
+print(pred_instance_map.shape)