Publications in AI

Using Pretrained models for prediction So today, I will tell you how to use pre-trained models.   For your existing images, you must follow specific steps. step one load the model step two, load image to be predicted. Step three, resize it. We resize since models were trained, using a specific size of pictures, and our target images must be resized before prediction. Step Four convert to NumPy array. We are doing this because images can be all in different formats. This can raise specific issues. So converting it to a form that Python can understand is a good idea for all images. Now we can predict after prediction, and we have to use the code predictions and find out the top few predictions. Now show to the user    Code: from tensorflow.keras.applications.resnet50 import ResNet50 from tensorflow.keras.preprocessing import image from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions import numpy as np model = R...

Links for Disease detection Brain Tumor Classification using Convolutional Neural Network | Kaggle Dataset | CNN Brain tumour Detection Breast Cancer Prediction Using Python and Machine Learning Alzheimer’s Disease Detection using Deep Learning Parkinson's Disease Detection using Machine Learning Detecting Skin Cancer (Melanoma) With Deep Learning Predicting Lungs Disease using Deep Learning Heart Disease Prediction using Machine Learning with Python

 My research is about creating a skin doctor, that will take a photograph and diagnose the skin condition. Initially. It will begin diagnosing to conditions for her skin is normal and or skin has some disease. If your skin is having some disease, it would diagnose for the kind of disease skin might have . In this research, we will be using Artificial intelligence techniques, such as deep learning and machine learning.  In order to increase the efficiency, they will take input from the patient and the image of skin condition to diagnose the correct situation of the skin.  We are using convolutional neural network coupled with in image, processing, algorithms and other algorithms that can increase the efficiency.