Anime Face Generation using DCGAN | Keras Tensorflow | Deep Learning | Python

⭐️ Content Description ⭐️
In this video, I have explained on how to generate anime faces using DCGAN (Generative Adversarial Network) with Keras and Tensorflow in Kaggle Notebook. This is an advanced deep learning project which we have to train 2 models, namely generator and discriminator. It will produce similar images to the train dataset as output.
Text-based Tutorial: www.hackersrealm.net/post/ani...
GitHub Code Repo: bit.ly/dlcoderepo
Dataset link: www.kaggle.com/datasets/soumi...
🌐 Website: www.hackersrealm.net
🔔 Subscribe: bit.ly/hackersrealm
🗓️ 1:1 Consultation with Me: calendly.com/hackersrealm/con...
📷 Instagram: / aswintechguy
🔣 Linkedin: / aswintechguy
🎯 GitHub: github.com/aswintechguy
🎬 Share: • Anime Face Generation ...
⚡️ Data Structures & Algorithms tutorial playlist: bit.ly/dsatutorial
😎 Hackerrank problem solving solutions playlist: bit.ly/hackerrankplaylist
🤖 ML projects tutorial playlist: bit.ly/mlprojectsplaylist
🐍 Python tutorial playlist: bit.ly/python3playlist
💻 Machine learning concepts playlist: bit.ly/mlconcepts
✍🏼 NLP concepts playlist: bit.ly/nlpconcepts
🕸️ Web scraping tutorial playlist: bit.ly/webscrapingplaylist
Make a small donation to support the channel 🙏🙏🙏:-
🆙 UPI ID: hackersrealm@apl
💲 PayPal: paypal.me/hackersrealm
🕒 Timeline
00:00 Introduction to DCGAN and Anime Dataset
03:32 Import Modules
06:59 Load the Dataset
09:58 Visualize Anime Images
14:08 Preprocess the Dataset
23:03 Create Generator Model
30:11 Create Discriminator Model
37:31 Create DCGAN Class
01:03:30 Create DCGAN Monitor Class
01:10:38 Train the Model
01:20:25 Generate New Anime Images
#dcgan #deeplearning #hackersrealm #anime #machinelearning #datascience #model #project #artificialintelligence #beginner #analysis #python #tutorial #aswin #ai #dataanalytics #data #bigdata #programming #datascientist #technology #coding #datavisualization #computerscience #pythonprogramming #analytics #tech #dataanalysis #iot #programmer #statistics #developer #ml #business #innovation #coder #dataanalyst

[@samsundar7095]

I appreciate your hard work but I didn't expect the anime content 🤣

[@HackersRealm]

haha... hardcore anime fan here!!!🤩

[@Kitsune152]

Thanks for this video, just what I was looking for. Neon Genesis Evangelion was the first anime I watched

[@HackersRealm]

that was a good one too!!!

[@Vedgadge-mm7vf]

I'm really excited to do this project, but right now I am not so familiar with CNN, so first I should learn that and I'll come back to this project

[@HackersRealm]

yes that could help you for better understanding of what's happening...

[@vanadin8009]

Don't you have an idea how can we deploy this model using gradio or streamlit

[@dheepanraj7489]

Can u pls help me out for creating a dataset for butterflies with color attribute.the model should learn the butterfly also on the color basis so when the user specifies a color the model should be able to produce an butterfly image similar to that colour

[@jagadeshwaranar3553]

Bro, is this project worth submitting as a final year project and kindly can you tell what can be the problem statement that this project is solving?

[@crickycricky9450]

i dont think so cause i think for final project you need to submit paper and u need work on the algorithm and detailed explanation of the result

[@lalitagarwal9155]

Sir I am unable to make flask app website using generator.h5 model, which I trained for around 10 hours using your jupyter notebook.

[@HackersRealm]

May I know what issue you're facing?

[@belalvai6653]

Bro can you please fix this error. I copied your code and tried it to another data set but it shows this and I can't solve --- ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (11500,) + inhomogeneous part.

[@alan-hf7gy]

Did you train it on kaggle gpu?and how long did it take to complete 50 epochs

[@HackersRealm]

yes, it took around an hour I guess

[@mrschef9468]

Can you please make a video on cyclegan human to anime or model

[@HackersRealm]

yes, there is a plan to cover all the gan models with different datasets...

[@evaggeliakyriakopoulou1404]

How can we plot the losses from generator and discriminator?

[@HackersRealm]

you can store the losses in a list and use it for the plot. I think the list is already there

[@PaoloTshiyole]

Nice video, so how about to deploy it on cloud maybe aws and make a public web site for everyone to use it I think the deployment will be a nice video after made a DCGan

[@HackersRealm]

I already shown how to do a local deployment using flask and other types of deployment can be done if needed... This is just for the tutorial purpose.

[@HafizAMalikh]

i want to generate 256X256 images and input images are also 256X256 but during epoch training it is showing 32/32 but for u it is showing 674/674 how to increase from 32/32 to 674/674

[@HackersRealm]

Are you referring to the batch size?

[@crickycricky9450]

bro im unable to add evalution metrics can you help me??

[@HackersRealm]

which eval metrics you're referring?

[@crickycricky9450]

@@HackersRealm psnr and gloss,dloss ones

[@agustastu4102]

great tutorial. do you have fiver. id like to ask you to join my project.

[@HackersRealm]

Hi, you can reach me via linkedin for brief discussion... link is in the description