You can deploy this model and start earning money today!

keviniacs/
Objects-Classifier-CNN

keras

Views

No views yet

Objects Classifier CNN

CNN for industrial parts classification in robotic automation systems.

Model Description

Trained to classify 3 types of industrial components:

screw: Metal screws and bolts
star: Star-shaped components
tee_connector: T-shaped pipe connectors

Performance

Accuracy: >85%
Inference time: ~100ms
Confidence threshold: 70% recommended
Framework: TensorFlow 2.20.0

Usage

python

import tensorflow as tf
import numpy as np
from PIL import Image

# Load model
model = tf.keras.models.load_model('mi_modelo_ia.keras')

# Preprocess image
img = Image.open('part.jpg').resize((224, 224))
img_array = np.array(img) / 255.0
img_array = np.expand_dims(img_array, axis=0)

# Predict
predictions = model.predict(img_array)
classes = ['screw', 'star', 'tee_connector']
result = classes[np.argmax(predictions)]
print(f"Detected: {result}")




ROS 2 Integration
Full robotic implementation: GitHub - UR5 Robot CNN Classifier

keviniacs/Objects-Classifier-CNN

Objects Classifier CNN

Model Description

Performance

Usage

keviniacs/
Objects-Classifier-CNN