Complete Computer Vision Bootcamp With PyTorch & Tensorflow
Год выпуска: 1/2025
Производитель: Udemy
Сайт производителя:
https://www.udemy.com/course/complete-computer-vision-bootcamp-with-pytoch-tensorflow/
Автор: Krish Naik, Sourangshu Pal, Monal kumar
Продолжительность: 52h 34m 26s
Тип раздаваемого материала: Видеоурок
Язык: Английский
Субтитры: Отсутствуют
Описание:
What you'll learn
- Master CNN concepts from basics to advanced with TensorFlow & PyTorch.
- Learn object detection models like YOLO and Faster R-CNN.
- Implement real-world computer vision projects step-by-step.
- Gain hands-on experience with data preprocessing and augmentation.
- Build custom CNN models for various computer vision tasks.
- Master transfer learning with pre-trained models like ResNet and VGG
- Gain practical skills with TensorFlow and PyTorch libraries
Requirements
- Basic understanding of Python programming.
- Familiarity with fundamental machine learning concepts.
- Knowledge of basic linear algebra and calculus.
- Understanding of image data and its structure.
- Enthusiasm to learn computer vision with hands-on projects.
Description
In this comprehensive course, you will master the fundamentals and advanced concepts of computer vision, focusing on Convolutional Neural Networks (CNN) and object detection models using TensorFlow and PyTorch. This course is designed to equip you with the skills required to build robust computer vision applications from scratch.
What You Will Learn
Throughout this course, you will gain expertise in:
- Introduction to Computer Vision
- Understanding image data and its structure.
- Exploring pixel values, channels, and color spaces.
- Learning about OpenCV for image manipulation and preprocessing.
- Deep Learning Fundamentals for Computer Vision
- Introduction to Neural Networks and Deep Learning concepts.
- Understanding backpropagation and gradient descent.
- Key concepts like activation functions, loss functions, and optimization techniques.
- Convolutional Neural Networks (CNN)
- Introduction to CNN architecture and its components.
- Understanding convolution layers, pooling layers, and fully connected layers.
- Implementing CNN models using TensorFlow and PyTorch.
- Data Augmentation and Preprocessing
- Techniques for improving model performance through data augmentation.
- Using libraries like imgaug, Albumentations, and TensorFlow Data Pipeline.
- Transfer Learning for Computer Vision
- Utilizing pre-trained models such as ResNet, VGG, and EfficientNet.
- Fine-tuning and optimizing transfer learning models.
- Object Detection Models
- Exploring object detection algorithms like:
- YOLO (You Only Look Once)
- Faster R-CNN
- Implementing these models with TensorFlow and PyTorch.
- Image Segmentation Techniques
- Understanding semantic and instance segmentation.
- Implementing U-Net and Mask R-CNN models.
- Real-World Projects and Applications
- Building practical computer vision projects such as:
- Face detection and recognition system.
- Real-time object detection with webcam integration.
- Image classification pipelines with deployment.
Who Should Enroll?
This course is ideal for:
- Beginners looking to start their computer vision journey.
- Data scientists and ML engineers wanting to expand their skill set.
- AI practitioners aiming to master object detection models.
- Researchers exploring computer vision techniques for academic projects.
- Professionals seeking practical experience in deploying CV models.
Prerequisites
Before enrolling, ensure you have:
- Basic knowledge of Python programming.
- Familiarity with fundamental machine learning concepts.
- Basic understanding of linear algebra and calculus.
Hands-on Learning with Real Projects
This course emphasizes practical learning through hands-on projects. Each module includes coding exercises, project implementations, and real-world examples to ensure you gain valuable skills.
By the end of this course, you will confidently build, train, and deploy computer vision models using TensorFlow and PyTorch. Whether you are a beginner or an experienced practitioner, this course will empower you with the expertise needed to excel in the field of computer vision.
Enroll now and take your computer vision skills to the next level!
Who this course is for:
- Beginners eager to learn computer vision from scratch.
- Data scientists looking to expand their skill set with CNN and object detection.
- AI and ML engineers aiming to build computer vision models.
- Researchers and students exploring deep learning for visual tasks.
- Professionals interested in deploying real-world CV applications
Формат видео: MP4
Видео: avc, 1280x720, 16:9, 30.000 к/с, 533 кб/с
Аудио: aac lc, 48.0 кгц, 128 кб/с, 2 аудио
MediaInfo
General
Complete name : D:\2\Udemy - Complete Computer Vision Bootcamp With PyTorch & Tensorflow (1.2025)\11 - Image Segmentation\2 -Downsampling.mp4
Format : MPEG-4
Format profile : Base Media
Codec ID : isom (isom/iso2/avc1/mp41)
File size : 83.2 MiB
Duration : 17 min 18 s
Overall bit rate : 672 kb/s
Frame rate : 30.000 FPS
Writing application : Lavf59.27.100
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
Format settings, GOP : M=4, N=60
Codec ID : avc1
Codec ID/Info : Advanced Video Coding
Duration : 17 min 18 s
Bit rate : 533 kb/s
Nominal bit rate : 3 000 kb/s
Maximum bit rate : 3 000 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) : 0.019
Stream size : 66.0 MiB (79%)
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=3000 / ratetol=1.0 / qcomp=0.60 / qpmin=0 / qpmax=69 / qpstep=4 / vbv_maxrate=3000 / vbv_bufsize=6000 / 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.709
Codec configuration box : avcC
Audio
ID : 2
Format : AAC LC
Format/Info : Advanced Audio Codec Low Complexity
Codec ID : mp4a-40-2
Duration : 17 min 18 s
Source duration : 17 min 18 s
Bit rate mode : Constant
Bit rate : 128 kb/s
Channel(s) : 2 channels
Channel layout : L R
Sampling rate : 48.0 kHz
Frame rate : 46.875 FPS (1024 SPF)
Compression mode : Lossy
Stream size : 15.8 MiB (19%)
Source stream size : 15.8 MiB (19%)
Default : Yes
Alternate group : 1
