Face Recognition using DeepFace library loss and accuracy test.

Mnist, Fashion MNist, Cifar 10, and Cifar 100.

• Classification between 4 animals: Elephant 🐘 dog 🐶 cat 🐈 Giraffe 🦒 Pandas 🐼

• Collect more than 200 photo data from each animal for Model training

• Using Augmentation To increase Train data

• Download the dataset from link below:

  • dataset

• Dataset	Loss	Accuracy
  VGG16	0.4215	0.8988
  Train	0.3229	0.9453
  Val	1.2178	0.6771
  test	1.3104	0.8929

• A deep learning model using VGG16 convolution neural net is trained to classify flowers 🌹🪴

• Download the dataset from link below:

  • dataset

• Dataset	Loss	Accuracy
  VGG16	0.4709	0.9188
  Train	0.1701	0.9453
  Val	1.3862	0.6497
  test	1.7977	0.6265

• A deep learning model using VGG16 convolution neural net is trained to classify 15 faces🧔🏻‍♂️👩🏽‍🦱👵🏻👨🏿‍🦲

• Download the dataset from link below:

  • dataset

• Dataset	Loss	Accuracy
  VGG16	0.5582	0.8881

• A deep learning model using MobileNetV2 Convolutional Neural Network is trained to recognize the human body 👳🏻‍♂️👨🏻
• Telegram Bot
• wandb
• Download the dataset from link below:
  • dataset

• Dataset	Loss	Accuracy
  Train	0.0093	0.9973
  Val	0.2555	0.9457

• Automatic estimation of human age based on the appearance of human face 👶🏻👵🏻,

• Using ResNet50V2 neural network

• Download the dataset from link below:

  • dataset

• wandb

• Dataset	Loss
  Train	9.2271
  Val	8.7625

• Extracts the text using easyOCR

resalt
	'Python', 'Web Apps','From Scratch'
	ازتو چشد تومی تابه,چشمه چشمه ابر ایثا,روى سينه ى توخو ابه,لوكدوم خليج سبزى
	DMC-4583
	29٧٢٨٤٣

• Vehicle license plate extraction using DTRB

  Train	Test
  73.918	73.998

• Download the dataset ,weights from link below dataset

pip install -r requirements.txt

Image name	predicted_labels	confidence score
	67e7737	0.9347
	97i48912	0.9987
	57c82374	0.9955
	73v96442	0.8017

Audio classification is a fundamental problem in the field of audio processing. It is a challenging problem because there is no clear definition of what is a good representation of audio data. In this project, we will use a custom dataset to classify audio files into 17 classes.Identify sounds in audio clips using Tensorflow and pydub 🗣

Run this command:

pip install -r requirements.txt

Download dataset

Extract it in the ./raw_audios directory.

Use make_dataset.ipynb notebook to convert the data into a dataset with format that can be used by the model.

Use Train.ipynb notebook to train the model.

In this face recognition project using InsightFace And pytorch is built 🧑

pip install -r requirements.txt

python3 FaceـVerification.py --image1 {yore imag1} --image2 {yore imag2}

A field of AI that enables machines to understand, generate, and interact with human language, revolutionizing content creation and chatbots. 📝

pip install -r requirements.txt

Download weights and glov.6b

ran file main is main.ipynb