Machine Learning Deep Learning Model Deployment
Год выпуска: 3/2023
Производитель: Udemy
Сайт производителя:
https://www.udemy.com/course/machine-learning-deep-learning-model-deployment/
Автор: FutureX Skills
Продолжительность: 5h 36m 56s
Тип раздаваемого материала: Видеоурок
Язык: Английский
Субтитры: Английский
Описание:
Serving TensorFlow Keras PyTorch Python model Flask Serverless REST API MLOps MLflow NLP Generative AI OpenAI GPT
What you'll learn
- Machine Learning Deep Learning Model Deployment techniques
- Simple Model building with Scikit-Learn , TensorFlow and PyTorch
- Deploying Machine Learning Models on cloud instances
- TensorFlow Serving and extracting weights from PyTorch Models
- Creating Serverless REST API for Machine Learning models
- Deploying tf-idf and text classifier models for Twitter sentiment analysis
- Deploying models using TensorFlow js and JavaScript
- Machine Learning experiment and deployment using MLflow
Requirements
- Prior Machine Learning and Deep Learning background required but not a must have as we are covering Model building process also
Description
In this course you will learn how to deploy Machine Learning Deep Learning Models using various techniques. This course takes you beyond model development and explains how the model can be consumed by different applications with hands-on examples
Course Structure:
- Creating a Classification Model using Scikit-learn
- Saving the Model and the standard Scaler
- Exporting the Model to another environment - Local and Google Colab
- Creating a REST API using Python Flask and using it locally
- Creating a Machine Learning REST API on a Cloud virtual server
- Creating a Serverless Machine Learning REST API using Cloud Functions
- Building and Deploying TensorFlow and Keras models using TensorFlow Serving
- Building and Deploying PyTorch Models
- Converting a PyTorch model to TensorFlow format using ONNX
- Creating REST API for Pytorch and TensorFlow Models
- Deploying tf-idf and text classifier models for Twitter sentiment analysis
- Deploying models using TensorFlow.js and JavaScript
- Tracking Model training experiments and deployment with MLFLow
- Running MLFlow on Colab and Databricks
Appendix - Generative AI - Miscellaneous Topics.
- OpenAI and the history of GPT models
- Creating an OpenAI account and invoking a text-to-speech model from Python code
- Invoking OpenAI Chat Completion, Text Generation, Image Generation models from Python code
- Creating a Chatbot with OpenAI API and ChatGPT Model using Python on Google Colab
- ChatGPT, Large Language Models (LLM) and prompt engineering
Python basics and Machine Learning model building with Scikit-learn will be covered in this course. This course is designed for beginners with no prior experience in Machine Learning and Deep Learning
You will also learn how to build and deploy a Neural Network using TensorFlow Keras and PyTorch. Google Cloud (GCP) free trial account is required to try out some of the labs designed for cloud environment.
Who this course is for:
- Machine Learning beginners
Формат видео: MP4
Видео: avc, 1920x1080, 16:9, 30.000 к/с, 535 кб/с
Аудио: aac lc sbr, 44.1 кгц, 62.8 кб/с, 2 аудио
MediaInfo
General
Complete name : D:\2_1\Udemy - Machine Learning Deep Learning model deployment (3.2023)\4 - Creating a REST API for the Machine Learning Model\15 - Deleting the VM instance.mp4
Format : MPEG-4
Format profile : Base Media
Codec ID : isom (isom/iso2/avc1/mp41)
File size : 3.46 MiB
Duration : 48 s 159 ms
Overall bit rate : 602 kb/s
Frame rate : 30.000 FPS
Recorded date : 2023-05-09 02:42:01.6274802+03:00
Writing application : Lavf59.27.100
Video
ID : 1
Format : AVC
Format/Info : Advanced Video Codec
Format profile : Main@L4
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 : 47 s 967 ms
Bit rate : 535 kb/s
Nominal bit rate : 800 kb/s
Width : 1 920 pixels
Height : 1 080 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) : 0.009
Stream size : 3.06 MiB (88%)
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=24 / lookahead_threads=4 / 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=800 / ratetol=1.0 / qcomp=0.60 / qpmin=0 / qpmax=69 / qpstep=4 / vbv_maxrate=800 / vbv_bufsize=1600 / nal_hrd=none / filler=0 / ip_ratio=1.40 / aq=1:1.00
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 : 48 s 159 ms
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 : 369 KiB (10%)
Title : und
Default : Yes
Alternate group : 1
