scfive commited on
Commit
ac8eec4
·
verified ·
1 Parent(s): 4ea2259

Upload 5 files

Browse files
README.roboflow.txt ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ roof damage - v4 2025-01-12 2:31pm
3
+ ==============================
4
+
5
+ This dataset was exported via roboflow.com on January 13, 2025 at 12:54 AM GMT
6
+
7
+ Roboflow is an end-to-end computer vision platform that helps you
8
+ * collaborate with your team on computer vision projects
9
+ * collect & organize images
10
+ * understand and search unstructured image data
11
+ * annotate, and create datasets
12
+ * export, train, and deploy computer vision models
13
+ * use active learning to improve your dataset over time
14
+
15
+ For state of the art Computer Vision training notebooks you can use with this dataset,
16
+ visit https://github.com/roboflow/notebooks
17
+
18
+ To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
19
+
20
+ The dataset includes 4922 images.
21
+ Damage are annotated in YOLOv11 format.
22
+
23
+ The following pre-processing was applied to each image:
24
+
25
+ No image augmentation techniques were applied.
26
+
27
+
approofysc5.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from ultralytics import YOLO
3
+ from PIL import Image
4
+ import numpy as np
5
+
6
+ # Load the YOLO model directly from the root directory
7
+ model_path = "best.pt" # Ensure this matches the exact name of your model file
8
+ model = YOLO(model_path)
9
+
10
+ # Streamlit app
11
+ st.title("YOLOv11 Object Detection")
12
+ st.write("Upload an image and let the model detect objects.")
13
+
14
+ uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])
15
+ if uploaded_file:
16
+ # Read and display the image
17
+ image = Image.open(uploaded_file)
18
+ st.image(image, caption="Uploaded Image", use_column_width=True)
19
+
20
+ # Perform prediction
21
+ with st.spinner("Processing..."):
22
+ results = model.predict(np.array(image))
23
+
24
+ # Display results
25
+ st.write("Detection Results:")
26
+ st.image(results[0].plot(), caption="Detections", use_column_width=True)
best (roofysc5).pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40b1f30fd772a3e9d2045552f5d47e2820d397e8793d8185d474b416469601c
3
+ size 19178067
data.yaml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ train: ../train/images
2
+ val: ../valid/images
3
+ test: ../test/images
4
+
5
+ nc: 10
6
+ names: ['Blister', 'Chipped Shingle', 'Cracked Shingle', 'Degranulation', 'Dragons Tooth', 'Hail Impac', 'Hail Impact', 'I-labeled-hail-damages-in-pics', 'Mechanical Damage', 'Puncture']
7
+
8
+ roboflow:
9
+ workspace: esper
10
+ project: roof-damage-vz2qc-oyrlz
11
+ version: 4
12
+ license: CC BY 4.0
13
+ url: https://app.roboflow.com/esper/roof-damage-vz2qc-oyrlz/4
requirements (roofysc5).txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ streamlit
2
+ ultralytics
3
+ Pillow
4
+ numpy