Added project

.gitattributes

@@ -24,6 +24,7 @@
 *.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+examples/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,68 @@
+import os
+import gradio as gr
+from ultralytics import YOLO
+import numpy as np
+
+model_options = ["yolov8n_bird_100.pt", "yolov8s_bird_100.pt", "yolov8m_bird_100.pt", "yolov8l_bird_100.pt"]
+model_names = ["Nano", "Small", "Medium", "Large"]
+print("before loading examples")
+example_list = [["./examples/" + example] for example in os.listdir("examples")]
+print("before loading models")
+models = [YOLO(os.path.join("./saved_model", option)) for option in model_options]
+print("finish preparation")
+
+def process_image(input_image, model_name, conf):
+    print('start processing: ')
+    if input_image is None:
+        return None, "No objects detected."
+
+    print(f"model_name : {model_name}")
+    print(f"conf : {conf}")
+
+    if model_name is None:
+        model_name = model_names[0]
+
+    if conf is None:
+        conf = 0.6
+
+    model_index = model_names.index(model_name)
+    print('model_index: ')
+    print(model_index)
+    model = models[model_index]
+    
+    results = model.predict(input_image, conf=conf)
+    class_counts = {}
+    class_counts_str = "Class Counts:\n"
+
+    for r in results:
+        im_array = r.plot()
+        im_array = im_array.astype(np.uint8)
+
+        if len(r.boxes) == 0:  # If no objects are detected
+            return None, "No objects detected."
+
+        for box in r.boxes:
+            class_name = r.names[box.cls[0].item()]
+            class_counts[class_name] = class_counts.get(class_name, 0) + 1
+
+        for cls, count in class_counts.items():
+            class_counts_str += f"\n{cls}: {count}"
+
+        return im_array, class_counts_str
+
+iface = gr.Interface(
+    fn=process_image,
+    inputs=[
+        gr.Image(), 
+        gr.Radio(model_names, label="Choose model", value=model_names[0]),
+        gr.Slider(minimum=0.2, maximum=1.0, step=0.1, label="Confidence Threshold", value=0.6)
+    ], 
+    outputs=["image", gr.Textbox(label="More info")],
+    title="YOLO Object detection. Trained on bird_1_3_dataset (millitary vehicles).",
+    description='''The bird_1_3_dataset dataset is composed of millitary vehicles.\n 
+                    https://universe.roboflow.com/arnold-gudima-t7mdj/bird_1_3 ''',
+    live=True,
+    examples=example_list
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio==3.49.0
+numpy==1.26.0
+opencv-python==4.9.0.80
+ultralytics==8.1.10
+mediapipe==0.10.7

saved_model/yolov8l_bird_100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0fb592ea934ab372a3650a222d31e2a2f2496feaaa40ddc8a0270666c4ba9a
+size 87644265

saved_model/yolov8m_bird_100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8723f8f8735c7c5d3604400e03b9c22a2412d24043b1c31cb144d1b87ce853d7
+size 52022913

saved_model/yolov8n_bird_100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d151e6934901348905535b7e88e8143a05d22739b5b8481dd8a0ea119d7cda
+size 6233433

saved_model/yolov8s_bird_100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87ab4d5ae02faf4a56fd6ae51d49b0899bdc705edef8a8178e726e6c7700757
+size 22506777