arnaldog12 / deep-learning Goto Github PK

View Code? Open in Web Editor NEW

82.0 10.0 42.0 31.71 MB

Study and implementation about deep learning models, architectures, applications and frameworks

Jupyter Notebook 89.07% Mathematica 0.01% Dockerfile 0.01% Python 0.17% HTML 10.74%

tensorflow tensorboard keras tflearn deep-learning deep-learning-algorithms

deep-learning's Introduction

Hi there 👋

I'm Arnaldo Gualberto, a Machine Learning and Deep Learning Engineer.

🍅 Machine Learning Analyst at Advolve.
Google Developer Expert in Machine Learning
PhD in Deep Learning by UFCG
Teacher at Udemy.
TensorFlow Developer Certificated

Things I am passionate about

📈 Machine Learning
🤖 Deep Learning
🧠 Neural Networks
👁️ Computer Vision
🔠 Natural Language Processing
💬 Large Language Models
TensorFlow

Get in touch

Visitor count

deep-learning's People

Contributors

Stargazers

Watchers

deep-learning's Issues

Model file missing

Hi, I couldn't find the models folder. Could you please share instructions to download the model?

├── data (unzip dataset here)
├── images
├── models
├── Keras.ipynb

[solved] google drive link for data shows error

can you please share the dataset i.e. correct link of dataset ?

Ho to find yaw, roll, and pitch for the training data?

Dear author,

Thank you so much for your work. I wanted to use face-alignment module to detect the keypoints and I was wondering how to find yaw, roll, and pitch for the training dataset?

Thanks

samples.rar and samples_old.rar error while extracting

Hi Arnaldo

For both the rar files on the google drive, error is coming while extracting.

Thanks
Rahul

Question: Re-training using 5 landmark points

Hi, Thanks for the inputs you shared on #6. The result looks good. Training was quite easy!

I'm planning to use the same method, but only with 5 landmark points (left and right eye center, nose tip, right and left mouth corners). The reason is that, MTCNN face detector outputs 5 landmark points and I'm planning to re-use the same and there by avoiding the dlib shape predictor.

Could you share your inputs? I agree that the number of features with 5 points would be very less when compared to 68 points. However, I'd like to get your inputs.

Thanks,
San

Samples.pkl not found

Hi Arnald, the data path you have provided returns a samples.rar which has sample_train.csv and sample_test.csv.

Could you please tell me how do I get the actual samples.pkl you used in your Keras.ipynb notebook?

SOTA for Head Pose Estimation on AFLW2000 dataset

Hi, check the link
https://paperswithcode.com/task/head-pose-estimation
contains papers and corresponding codes for head-pose-estimation from single image

Larger Data set

i am so grateful for your work in this model, but can i get access to a larger dataset? or can you explain how did you create the toy database, as it's not available to get more face images and convert them to facial encodings etc..
thanks in advance

FPS issue for the real-time experinece in Webcam

Hi,
Can you tell me how can i increase it's Fps as it is only 0.87 right now which is not good for the real time experience.

Is there a C++ evaluation file of this model??

Hi,

I trained the model in Keras but want to use it in C++ for evaluation, do you have a C++ evaluation file of this model??
It would be very helpful for me if you can share any C++ code regarding this model and have files in which the C++ version of this model can be evaluated. I am new to C++ and have issues in making functions like compute_features() and detect_face_points() in C++
Any help would be appreciated!!