Скачать или смотреть 16-DCGAN from Scratch with Tensorflow - Create Fake Images from CELEB-A Dataset | Deep Learning

🔥🐍 Checkout the MASSIVELY UPGRADED 2nd Edition of my Book (with 1300+ pages of Dense Python Knowledge) Covering 350+ Python 🐍 Core concepts

🟠 Book Link - https://rohanpaul.gumroad.com/l/pytho...

---------------------

Hi, I am a Machine Learning Engineer | Kaggle Master. Connect with me on 🐦 TWITTER:   / rohanpaul_ai   - for daily in-depth coverage of Machine Learning / LLM / OpenAI / LangChain / Python Intricacies Topics.


Deep Convolutional GANs (DCGANs) introduced convolutions to the generator and discriminator networks. In this video, I am implementing Deep Convolutional GANs (DCGANs) from scratch to create Fake Images.

👉 Link to PART-2 - Video Explaining in detail the Generator() Function and its filter_size, input_shape of DCGAN -    • 38-DCGAN's Generator Function - Understand...  

👉 Github Repo - https://bit.ly/3QTCZw2

👉 Link to my Kaggle Notebook - https://www.kaggle.com/paulrohan2020/...

👉 Kaggle Dataset - https://www.kaggle.com/jessicali9530/...

👉 DCGAN Original Paper - https://arxiv.org/abs/1511.06434

@0:00 Intro
@2:20 Fundamentals of GAN
@4:50 Normal Neural Network vs Convolutional Neural Network
@6:32 DCGAN - Deep Convolutional GANs Architecture
@10:00 Deep Convolutional GANs Original Paper Reading
@13:55 Start of Coding from scratch of Deep Convolutional GANs - Get Data in Google Colab
@18:14 Preprocessing and getting CELEB-A dataset ready for DCGAN training
@35:41 Generator Network of DCGAN (Deep Convolutional GANs) - Coding from Scratch
@38:37 What is Transpose of a CNN or Conv2DTranspose Function of Keras
@42:23 Conv2DTranspose of Keras - Explanations of Function Arguments
@49:29 Discriminator Network of DCGAN (Deep Convolutional GANs ) - Coding from Scratch
@52:22 Why setting discriminator.trainable to False during model compilation of Deep Convolutional GANs
@53:27 Overall architecture or Framework of DCGAN (Deep Convolutional GANs ) Training
@55:32 Final Training Code of DCGAN (Deep Convolutional GANs ) for CELEB-A dataset

Here is the summary of DCGAN:
Replace all max pooling with convolutional stride
Use transposed convolution for upsampling.
Eliminate fully connected layers.
Use Batch normalization except the output layer for the generator and the input layer of the discriminator.
Use ReLU in the generator except for the output which uses tanh.
Use LeakyReLU in the discriminator.

----------------

🚀🔬 Checkout my Generative Adversarial Network (GAN) video course in Gumroad -

7.5 Hours of Course - 6 different GAN Architecture implementations from scratch with #PyTorch

🚀🔬 https://bit.ly/3Ozcf3y

You can find me here:

**********************************************
👨🏻‍💼 LINKEDIN:   / rohan-paul-b27285129  
🐦 TWITTER:   / rohanpaul_ai  
🟠 Substack : https://rohanpaul.substack.com/
👨‍🔧 Kaggle: https://www.kaggle.com/paulrohan2020
👨‍💻 GITHUB: https://github.com/rohan-paul
📸 Instagram:   / rohan_paul_2020  
🟠 My YouTube-Finance Channel: https://www.youtube.com/@paulrohan/vi...

**********************************************


Other Playlist you might like 👇

🟠 MachineLearning & DeepLearning Concepts & interview Question Playlist - https://bit.ly/380eYDj

🟠 ComputerVision / DeepLearning Algorithms Implementation Playlist - https://bit.ly/36jEvpI

🟠 DataScience | MachineLearning Projects Implementation Playlist - https://bit.ly/39MEigt

🟠 Natural Language Processing Playlist : https://bit.ly/3P6r2CL



#machinelearning #datascience #nlp #textprocessing #kaggle #tensorflow #pytorch #deeplearning #deeplearningai #100daysofmlcode #neuralnetworks #pythonprogramming #python #100DaysOfMLCode