|
import streamlit as st
|
|
|
|
from utils.functional import generate_empty_space, set_page_config
|
|
|
|
|
|
set_page_config("Glossary", "📚")
|
|
generate_empty_space(1)
|
|
|
|
st.write(
|
|
"- Artificial Intelligence 🤖: The ability of machines to perform tasks that would normally require human intelligence, such as visual perception, speech recognition, decision-making, and language translation."
|
|
)
|
|
st.write(
|
|
"- Machine Learning 🧠: A subfield of AI that enables machines to learn from data without being explicitly programmed. It involves the use of algorithms that can learn and improve from experience."
|
|
)
|
|
st.write(
|
|
"- Deep Learning 🤯: A type of machine learning that uses neural networks to process and analyze large amounts of data. It involves multiple layers of artificial neurons that can learn complex patterns and relationships."
|
|
)
|
|
st.write(
|
|
"- Computer Vision 👀: A field of AI that focuses on enabling machines to interpret and understand visual data from the world, such as images and videos."
|
|
)
|
|
st.write(
|
|
"- Model Deep Learning 🧮: A mathematical representation of a deep learning algorithm that can be used to make predictions or classifications based on input data."
|
|
)
|
|
st.write(
|
|
"- resnet50 🤖: A popular deep learning model used for image classification, object detection, and other computer vision tasks. It has 50 layers and uses residual connections to improve training."
|
|
)
|
|
st.write(
|
|
"- vgg16 🤖: Another popular deep learning model for image classification. It has 16 layers and uses small convolutional filters."
|
|
)
|
|
st.write(
|
|
"- inception_v4 🤖: A deep learning model that uses inception modules to capture both local and global features in images. It is known for its high accuracy in image classification tasks."
|
|
)
|
|
st.write(
|
|
"- efficientnet_b4 🤖: A deep learning model that is designed to be more efficient and accurate than previous models. It uses a combination of scaling, squeezing, and excitation techniques to improve performance."
|
|
)
|
|
st.write(
|
|
"- mobilenetv3_large_100 🤖: A deep learning model that is designed to be lightweight and fast, making it ideal for mobile and embedded devices. It has high accuracy in image classification tasks."
|
|
)
|
|
st.write(
|
|
"- densenet121 🤖: A deep learning model that uses dense connections between layers to improve training and reduce the number of parameters needed."
|
|
)
|
|
st.write(
|
|
"- vit_base_patch16_224_dino 🤖: A deep learning model that uses a transformer architecture for image classification tasks. It has achieved state-of-the-art performance in some benchmarks."
|
|
)
|
|
st.write(
|
|
"- clip 🤖: A deep learning model that can understand and generate natural language descriptions of images and videos. It uses a contrastive learning approach to learn joint representations of text and images."
|
|
)
|
|
st.write(
|
|
"- Image Classification 📷: The process of assigning a label or category to an image based on its visual content."
|
|
)
|
|
st.write(
|
|
"- Face Detection 😷: The process of locating and identifying human faces in images or videos."
|
|
)
|
|
st.write(
|
|
"- Prototypical Networks 🤝: A type of few-shot learning algorithm that learns a prototype representation of each class based on a few examples. It can be used for tasks such as image classification and object detection."
|
|
)
|
|
st.write(
|
|
"- Grad-CAM 🌡️: A technique for visualizing the regions of an image that a deep learning model uses to make a prediction. It can help to interpret and explain the model's behavior."
|
|
)
|
|
st.write(
|
|
"- Support Set 🤝: A type of machine learning that involves training a model on a small number of examples from each class. It can be used for tasks such as image classification and object detection."
|
|
)
|
|
st.write(
|
|
"- Freeze Model ❄️: The process of fixing the weights of a deep learning model during training to prevent them from being updated. This is often done when fine-tuning a pre-trained model."
|
|
)
|
|
st.write(
|
|
"- Pretrained Model 🎓: A deep learning model that has been trained on a large dataset and can be used as a starting point for other tasks."
|
|
)
|
|
st.write(
|
|
"- Confidence Score 🎯: A measure of how confident a deep learning model is in its predictions. It is often represented as a probability between 0 and 1."
|
|
)
|
|
st.write(
|
|
"- Similarity Score 📊: A metric that measures how similar two things are based on a certain criteria or feature."
|
|
)
|
|
st.write(
|
|
"- Inference Time ⏱️: The time it takes for an AI model to make a prediction or inference on a new input. It is an important metric for measuring the speed and efficiency of an AI system."
|
|
)
|
|
st.write(
|
|
"- Image Embeddings 🖼️: A compact numerical representation of an image that captures its features and can be used for tasks such as image similarity and search."
|
|
)
|
|
st.write(
|
|
"- Zero Shot Image Classification 🚫: A type of image classification that can recognize classes that were not present in the training data. It is achieved by using a pre-trained model and leveraging semantic relationships between classes"
|
|
)
|
|
st.write(
|
|
"- Streamlit 🌊: An open-source framework used for building web applications for machine learning and data science. It allows developers to quickly create and share interactive applications without requiring knowledge of web development."
|
|
)
|
|
st.write(
|
|
"- Anime 🎌: A style of Japanese animation that often features colorful graphics, vibrant characters, and fantastical themes."
|
|
)
|
|
st.write(
|
|
"- Hunter X Hunter 📖: A popular Japanese manga and anime series about a young boy named Gon Freecss who aspires to become a professional Hunter and search for his father. The series is known for its complex characters and intricate storyline."
|
|
)
|
|
|
