Deep Learning Masterclass with TensorFlow 2 Over 20 Projects
Год выпуска: 4/2024
Производитель: Udemy
Сайт производителя:
https://www.udemy.com/course/deep-learning-masterclass-with-tensorflow-2-over-15-projects/
Автор: Neuralearn Dot AI
Продолжительность: 67h 10m 39s
Тип раздаваемого материала: Видеоурок
Язык: Английский
Субтитры: Английский
Описание:
What you'll learn
- The Basics of Tensors and Variables with Tensorflow
- Basics of Tensorflow and training neural networks with TensorFlow 2.
- Convolutional Neural Networks applied to Malaria Detection
- Building more advanced Tensorflow models with Functional API, Model Subclassing and Custom Layers
- Evaluating Classification Models using different metrics like: Precision,Recall,Accuracy and F1-score
- Classification Model Evaluation with Confusion Matrix and ROC Curve
- Tensorflow Callbacks, Learning Rate Scheduling and Model Check-pointing
- Mitigating Overfitting and Underfitting with Dropout, Regularization, Data augmentation
- Data augmentation with TensorFlow using TensorFlow image and Keras Layers
- Advanced augmentation strategies like Cutmix and Mixup
- Data augmentation with Albumentations with TensorFlow 2 and PyTorch
- Custom Loss and Metrics in TensorFlow 2
- Eager and Graph Modes in TensorFlow 2
- Custom Training Loops in TensorFlow 2
- Integrating Tensorboard with TensorFlow 2 for data logging, viewing model graphs, hyperparameter tuning and profiling
- Machine Learning Operations (MLOps) with Weights and Biases
- Experiment tracking with Wandb
- Hyperparameter tuning with Wandb
- Dataset versioning with Wandb
- Model versioning with Wandb
- Human emotions detection
- Modern convolutional neural networks(Alexnet, Vggnet, Resnet, Mobilenet, EfficientNet)
- Transfer learning
- Visualizing convnet intermediate layers
- Grad-cam method
- Model ensembling and class imbalance
- Transformers in Vision
- Model deployment
- Conversion from tensorflow to Onnx Model
- Quantization Aware training
- Building API with Fastapi
- Deploying API to the Cloud
- Object detection from scratch with YOLO
- Image Segmentation from scratch with UNET model
- People Counting from scratch with Csrnet
- Digit generation with Variational autoencoders (VAE)
- Face generation with Generative adversarial neural networks (GAN)
- Sentiment Analysis with Recurrent neural networks, Attention Models and Transformers from scratch
- Neural Machine Translation with Recurrent neural networks, Attention Models and Transformers from scratch
- Intent Classification with Deberta in Huggingface transformers
- Neural Machine Translation with T5 in Huggingface transformers
- Extractive Question Answering with Longformer in Huggingface transformers
- E-commerce search engine with Sentence transformers
- Lyrics Generator with GPT2 in Huggingface transformers
- Grammatical Error Correction with T5 in Huggingface transformers
- Elon Musk Bot with BlenderBot in Huggingface transformers
Requirements
- Basic Math
- Access to an internet connection, as we shall be using Google Colab (free version)
- Basic Knowledge of Python
Description
Deep Learning is one of the most popular fields in computer science today. It has applications in many and very varied domains. With the publishing of much more efficient deep learning models in the early 2010s, we have seen a great improvement in the state of the art in domains like
Computer Vision, Natural Language Processing, Image Generation, and Signal Processing.
The
demand for Deep Learning engineers is skyrocketing and experts in this field are
highly paid, because of their value. However, getting started in this field isn’t easy. There’s so much information out there, much of which is outdated and many times don't take the beginners into consideration
In this course, we shall take you on an amazing journey in which you'll master different concepts with a step-by-step and project-based approach. You shall be using
Tensorflow 2 (the world's most popular library for deep learning, and built by Google) and
Huggingface. We shall start by understanding how to build very simple models (like Linear regression models for
car price prediction, text classifiers for
movie reviews, binary classifiers for
malaria prediction) using Tensorflow and Huggingface transformers, to more advanced models (like object detection models with
YOLO, lyrics generator model with
GPT2 and Image generation with
GANs)
After going through this course and carrying out the different projects, you will develop the skill sets needed to develop modern deep-learning solutions that big tech companies encounter.
You will learn:
- The Basics of Tensorflow (Tensors, Model building, training, and evaluation)
- Deep Learning algorithms like Convolutional neural networks and Vision Transformers
- Evaluation of Classification Models (Precision, Recall, Accuracy, F1-score, Confusion Matrix, ROC Curve)
- Mitigating overfitting with Data augmentation
- Advanced Tensorflow concepts like Custom Losses and Metrics, Eager and Graph Modes and Custom Training Loops, Tensorboard
- Machine Learning Operations (MLOps) with Weights and Biases (Experiment Tracking, Hyperparameter Tuning, Dataset Versioning, Model Versioning)
- Binary Classification with Malaria detection
- Multi-class Classification with Human Emotions Detection
- Transfer learning with modern Convnets (Vggnet, Resnet, Mobilenet, Efficientnet) and Vision Transformers (VITs)
- Object Detection with YOLO (You Only Look Once)
- Image Segmentation with UNet
- People Counting with Csrnet
- Model Deployment (Distillation, Onnx format, Quantization, Fastapi, Heroku Cloud)
- Digit generation with Variational Autoencoders
- Face generation with Generative Adversarial Neural Networks
- Text Preprocessing for Natural Language Processing.
- Deep Learning algorithms like Recurrent Neural Networks, Attention Models, Transformers, and Convolutional neural networks.
- Sentiment analysis with RNNs, Transformers, and Huggingface Transformers (Deberta)
- Transfer learning with Word2vec and modern Transformers (GPT, Bert, ULmfit, Deberta, T5...)
- Machine translation with RNNs, attention, transformers, and Huggingface Transformers (T5)
- Model Deployment (Onnx format, Quantization, Fastapi, Heroku Cloud)
- Intent Classification with Deberta in Huggingface transformers
- Named Entity Relation with Roberta in Huggingface transformers
- Neural Machine Translation with T5 in Huggingface transformers
- Extractive Question Answering with Longformer in Huggingface transformers
- E-commerce search engine with Sentence transformers
- Lyrics Generator with GPT2 in Huggingface transformers
- Grammatical Error Correction with T5 in Huggingface transformers
- Elon Musk Bot with BlenderBot in Huggingface transformers
- Speech recognition with RNNs
If you are willing to move a
step further in your career, this course is destined for you and we are super excited to help achieve your goals!
This course is offered to you by
Neuralearn. And just like every other course by Neuralearn, we lay much emphasis on feedback. Your reviews and questions in the forum will help us better this course. Feel free to ask as many questions as possible on the forum. We do our very best to reply in the shortest possible time.
Enjoy!!!
Who this course is for:
- Beginner Python Developers curious about Applying Deep Learning for Computer vision and Natural Language Processing
- Deep Learning for Computer vision Practitioners who want gain a mastery of how things work under the hood
- Anyone who wants to master deep learning fundamentals and also practice deep learning for computer vision using best practices in TensorFlow.
- Computer Vision practitioners who want to learn how state of art computer vision models are built and trained using deep learning.
- Natural Language Processing practitioners who want to learn how state of art NLP models are built and trained using deep learning.
- Anyone wanting to deploy ML Models
- Learners who want a practical approach to Deep learning for Computer vision, Natural Language Processing and Sound recognition
Формат видео: MP4
Видео: avc, 1280x720, 16:9, 30.000 к/с, 484 кб/с
Аудио: aac lc sbr, 44.1 кгц, 62.8 кб/с, 2 аудио
Изменения/Changes
The 2024/4 version has a reduction of 100 lessons and a duration of 32 hours and 26 minutes compared to the 2023/2 version.
MediaInfo
General
Complete name : D:\2\Udemy - Deep Learning Masterclass with TensorFlow 2 Over 20 Projects (4.2024)\21. People counting\04. CSRNET.mp4
Format : MPEG-4
Format profile : Base Media
Codec ID : isom (isom/iso2/avc1/mp41)
File size : 28.5 MiB
Duration : 7 min 11 s
Overall bit rate : 553 kb/s
Frame rate : 30.000 FPS
Writing application : Lavf61.9.100
Video
ID : 1
Format : AVC
Format/Info : Advanced Video Codec
Format profile : Main@L3.1
Format settings : CABAC / 4 Ref Frames
Format settings, CABAC : Yes
Format settings, Reference frames : 4 frames
Codec ID : avc1
Codec ID/Info : Advanced Video Coding
Duration : 7 min 11 s
Bit rate : 484 kb/s
Nominal bit rate : 600 kb/s
Width : 1 280 pixels
Height : 720 pixels
Display aspect ratio : 16:9
Frame rate mode : Constant
Frame rate : 30.000 FPS
Color space : YUV
Chroma subsampling : 4:2:0
Bit depth : 8 bits
Scan type : Progressive
Bits/(Pixel*Frame) : 0.018
Stream size : 24.9 MiB (87%)
Writing library : x264 core 164 r3095 baee400
Encoding settings : cabac=1 / ref=3 / deblock=1:0:0 / analyse=0x1:0x111 / me=umh / subme=6 / psy=1 / psy_rd=1.00:0.00 / mixed_ref=1 / me_range=16 / chroma_me=1 / trellis=1 / 8x8dct=0 / cqm=0 / deadzone=21,11 / fast_pskip=1 / chroma_qp_offset=-2 / threads=22 / lookahead_threads=3 / sliced_threads=0 / nr=0 / decimate=1 / interlaced=0 / bluray_compat=0 / constrained_intra=0 / bframes=3 / b_pyramid=2 / b_adapt=1 / b_bias=0 / direct=1 / weightb=1 / open_gop=0 / weightp=2 / keyint=60 / keyint_min=6 / scenecut=0 / intra_refresh=0 / rc_lookahead=60 / rc=cbr / mbtree=1 / bitrate=600 / ratetol=1.0 / qcomp=0.60 / qpmin=0 / qpmax=69 / qpstep=4 / vbv_maxrate=600 / vbv_bufsize=1200 / nal_hrd=none / filler=0 / ip_ratio=1.40 / aq=1:1.00
Color range : Limited
Color primaries : BT.709
Transfer characteristics : BT.709
Matrix coefficients : BT.601
Codec configuration box : avcC
Audio
ID : 2
Format : AAC LC SBR
Format/Info : Advanced Audio Codec Low Complexity with Spectral Band Replication
Commercial name : HE-AAC
Format settings : Explicit
Codec ID : mp4a-40-2
Duration : 7 min 11 s
Bit rate mode : Constant
Bit rate : 62.8 kb/s
Channel(s) : 2 channels
Channel layout : L R
Sampling rate : 44.1 kHz
Frame rate : 21.533 FPS (2048 SPF)
Compression mode : Lossy
Stream size : 3.23 MiB (11%)
Language : English
Default : Yes
Alternate group : 1
