update yo yolo11

README.md

@@ -1,5 +1,5 @@
 ---
-title: Small Object Detection with YOLOv5
+title: Small Object Detection with YOLO11
 emoji: 🔭
 colorFrom: pink
 colorTo: yellow

app.py

@@ -5,6 +5,15 @@ import sahi.predict
 import sahi.slicing
 from PIL import Image
 import numpy
+from ultralytics import YOLO
+
+
+import sys
+import types
+if 'huggingface_hub.utils._errors' not in sys.modules:
+    mock_errors = types.ModuleType('_errors')
+    mock_errors.RepositoryNotFoundError = Exception
+    sys.modules['huggingface_hub.utils._errors'] = mock_errors
 
 IMAGE_SIZE = 640
 
@@ -31,7 +40,7 @@ sahi.utils.file.download_from_url(
 
 # Model
 model = AutoDetectionModel.from_pretrained(
-    model_type="yolov5", model_path="yolov5s6.pt", device="cpu", confidence_threshold=0.5, image_size=IMAGE_SIZE
+    model_type="ultralytics", model_path="yolo11s.pt", device="cpu", confidence_threshold=0.5, image_size=IMAGE_SIZE
 )
 
 
@@ -98,10 +107,10 @@ def sahi_yolo_inference(
 
 inputs = [
     gr.Image(type="pil", label="Original Image"),
-    gr.Number(default=512, label="slice_height"),
-    gr.Number(default=512, label="slice_width"),
-    gr.Number(default=0.2, label="overlap_height_ratio"),
-    gr.Number(default=0.2, label="overlap_width_ratio"),
+    gr.Number(value=512, label="slice_height"),
+    gr.Number(value=512, label="slice_width"),
+    gr.Number(value=0.2, label="overlap_height_ratio"),
+    gr.Number(value=0.2, label="overlap_width_ratio"),
     gr.Dropdown(
         ["NMS", "GREEDYNMM"],
         type="value",
@@ -109,20 +118,20 @@ inputs = [
         label="postprocess_type",
     ),
     gr.Dropdown(
-        ["IOU", "IOS"], type="value", default="IOU", label="postprocess_type"
+        ["IOU", "IOS"], type="value", value="IOU", label="postprocess_type"
     ),
-    gr.Number(default=0.5, label="postprocess_match_threshold"),
-    gr.Checkbox(default=True, label="postprocess_class_agnostic"),
+    gr.Number(value=0.5, label="postprocess_match_threshold"),
+    gr.Checkbox(value=True, label="postprocess_class_agnostic"),
 ]
 
 outputs = [
-    gr.Image(type="pil", label="YOLOv5s"),
-    gr.Image(type="pil", label="YOLOv5s + SAHI"),
+    gr.Image(type="pil", label="YOLO11s Standard"),
+    gr.Image(type="pil", label="YOLO11s + SAHI Sliced"),
 ]
 
-title = "Small Object Detection with SAHI + YOLOv5"
-description = "SAHI + YOLOv5 demo for small object detection. Upload an image or click an example image to use."
-article = "<p style='text-align: center'>SAHI is a lightweight vision library for performing large scale object detection/ instance segmentation.. <a href='https://github.com/obss/sahi'>SAHI Github</a> | <a href='https://medium.com/codable/sahi-a-vision-library-for-performing-sliced-inference-on-large-images-small-objects-c8b086af3b80'>SAHI Blog</a> | <a href='https://github.com/fcakyon/yolov5-pip'>YOLOv5 Github</a> </p>"
+title = "Small Object Detection with SAHI + YOLO11"
+description = "SAHI + YOLO11 demo for small object detection. Upload your own image or click an example image to use."
+article = "<p style='text-align: center'>SAHI is a lightweight vision library for performing large scale object detection/ instance segmentation.. <a href='https://github.com/obss/sahi'>SAHI Github</a> | <a href='https://medium.com/codable/sahi-a-vision-library-for-performing-sliced-inference-on-large-images-small-objects-c8b086af3b80'>SAHI Blog</a> </p>"
 examples = [
     ["apple_tree.jpg", 256, 256, 0.2, 0.2, "NMS", "IOU", 0.4, True],
     ["highway.jpg", 256, 256, 0.2, 0.2, "NMS", "IOU", 0.4, True],
@@ -140,4 +149,4 @@ gr.Interface(
     examples=examples,
     theme="huggingface",
     cache_examples=True,
-).launch(debug=True, enable_queue=True)
+).launch(debug=True)

packages.txt

@@ -1,3 +1,3 @@
 ffmpeg
 libsm6
-libxext6
+libxext6

requirements.txt

@@ -1,5 +1,8 @@
-torch==1.12.0+cpu
-torchvision==0.13.0+cpu
--f https://download.pytorch.org/whl/torch_stable.html
-yolov5==7.0.8
-sahi==0.11.11
+torch>=1.11.0
+torchvision>=0.12.0
+sahi>=0.11.0
+numpy<2.0.0
+gradio>=3.0.0
+Pillow>=8.0.0
+opencv-python>=4.5.0
+ultralytics