upload files

README.dataset.txt

@@ -0,0 +1,6 @@
+# Motherboard > motherboard_5
+https://universe.roboflow.com/yuelin-xin/motherboard-ptxx1
+
+Provided by a Roboflow user
+License: CC BY 4.0
+

README.roboflow.txt

@@ -0,0 +1,33 @@
+
+Motherboard - v13 motherboard_5
+==============================
+
+This dataset was exported via roboflow.com on February 14, 2023 at 11:35 PM GMT
+
+Roboflow is an end-to-end computer vision platform that helps you
+* collaborate with your team on computer vision projects
+* collect & organize images
+* understand and search unstructured image data
+* annotate, and create datasets
+* export, train, and deploy computer vision models
+* use active learning to improve your dataset over time
+
+For state of the art Computer Vision training notebooks you can use with this dataset,
+visit https://github.com/roboflow/notebooks
+
+To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
+
+The dataset includes 1015 images.
+Screws are annotated in YOLOv8 format.
+
+The following pre-processing was applied to each image:
+* Auto-orientation of pixel data (with EXIF-orientation stripping)
+* Resize to 1000x1000 (Stretch)
+* Auto-contrast via adaptive equalization
+
+The following augmentation was applied to create 3 versions of each source image:
+* 50% probability of horizontal flip
+* Equal probability of one of the following 90-degree rotations: none, clockwise, counter-clockwise
+* Random exposure adjustment of between -25 and +25 percent
+
+

data.yaml

@@ -0,0 +1,13 @@
+train: "set your training data path here"
+val: "set your validation data path here"
+test: "set your test data path here"
+
+nc: 11
+names: ['CPU_FAN_NO_Screws', 'CPU_FAN_Screw_loose', 'CPU_FAN_Screws', 'CPU_fan', 'CPU_fan_port', 'CPU_fan_port_detached', 'Incorrect_Screws', 'Loose_Screws', 'No_Screws', 'Scratch', 'Screws']
+
+roboflow:
+  workspace: yuelin-xin
+  project: motherboard-ptxx1
+  version: 13
+  license: CC BY 4.0
+  url: https://universe.roboflow.com/yuelin-xin/motherboard-ptxx1/dataset/13s

inference.py

@@ -0,0 +1,20 @@
+# Import Libraries
+
+from ultralytics import YOLO
+import warnings
+warnings.filterwarnings('ignore')
+
+# Define testing image
+image = "path to your testing image"
+# Set the weight
+model = YOLO("best.pt")
+# Start prediction on the testing image
+results = model.predict(source=image,conf=0.5, save=True) # save=True allow us to save the predicted image
+# Retrieved training labels
+names = model.names
+
+# Loop to display predicted labels
+for r in results:
+    for c in r.boxes.cls:
+        predicted_label = names[int(c)]
+        print(f" Predicted Labels are : {predicted_label}")

inspection_webapp.py

@@ -0,0 +1,78 @@
+import PIL
+import streamlit as st
+from ultralytics import YOLO
+
+# Give the path of the best.pt (best weights)
+model_path = 'best.pt'
+
+# Setting page layout
+st.set_page_config(
+    page_title="MOTHERBOARD DEFECT INSPECTION WEBAPP SYSTEM)",  # Setting page title
+    page_icon="image path to be the webapp icon",     # Setting page icon
+    layout="wide",      # Setting layout to wide
+    initial_sidebar_state="expanded",    # Expanding sidebar by default
+
+)
+
+# Creating sidebar
+with st.sidebar:
+    st.header("Image Config")     # Adding header to sidebar
+    # Adding file uploader to sidebar for selecting images
+    source_img = st.file_uploader(
+        "Upload an image...", type=("jpg", "jpeg", "png", 'bmp', 'webp'))
+
+    # Model Options
+    confidence = float(st.slider(
+        "Select Model Confidence", 25, 100, 40)) / 100
+
+# Creating main page heading
+st.title("MOTHERBOARD DEFECT INSPECTION WEBAPP SYSTEM")
+st.caption('Updload a photo by selecting :blue[Browse files]')
+st.caption('Then click the :blue[Detect Objects] button and check the result.')
+# Creating two columns on the main page
+col1, col2 = st.columns(2)
+
+# Adding image to the first column if image is uploaded
+with col1:
+    if source_img:
+        # Opening the uploaded image
+        uploaded_image = PIL.Image.open(source_img)
+        image_width, image_height = (644, 644) #uploaded_image.size
+        # Adding the uploaded image to the page with a caption
+        st.image(source_img,
+                 caption="Uploaded Image",
+                 width=image_width
+                 )
+
+try:
+    model = YOLO(model_path)
+except Exception as ex:
+    st.error(
+        f"Unable to load model. Check the specified path: {model_path}")
+    st.error(ex)
+
+if st.sidebar.button('INSPECT'):
+    results = model.predict(uploaded_image,
+                        conf=confidence,
+                        line_width=3, 
+                        show_labels=True, 
+                        show_conf=False
+                        )
+    boxes = results[0].boxes
+    results_plotted = results[0].plot(labels=True, line_width=4)[:, :, ::-1]
+    with col2:
+        st.image(results_plotted,
+                 caption='Detected Image',
+                 width=image_width                 
+                 )
+        try:
+            names = model.names
+            st.write(f'Number of detected objects: {len(boxes)}')
+            predicted_label = list()
+            for r in results:
+                for c in r.boxes.cls:
+                    predicted_label = names[int(c)]
+                    st.text(predicted_label)
+
+        except Exception as ex:
+            st.write("No image is uploaded yet!")

train_main.py

@@ -0,0 +1,10 @@
+from ultralytics import YOLO
+
+# Load the model.
+model = YOLO('yolov8n.pt')
+
+model.train(
+   data='data.yaml',
+   imgsz=1000,
+   batch=4,
+   epochs=1000)