Train Deep Learning Models On 25,000 images + Keywords
€750-1500 EUR
Annulleret
Slået op næsten 8 år siden
€750-1500 EUR
Betales ved levering
We have a database of 25,000 high quality images, with about 20 keywords per image. The keywords include purely descriptive elements, such as "lion", "table", or "eating", "running", but also more conceptual notions, such as "joy", "loneliness", "friendship". We need you to do 3 things:
1- Separate the conceptual keywords from the others, using a Python or R script with appropriate NLP libraries
2- Define and train a first model to predict the "concepts", based on the other keywords.
3- Define and train a second model based on the images themselves.
For 2- and 3-, we expect you to use a Deep Learning library, such as Tensorflow. We will ask you to provide the model and and script used to prepare the data (keywords/images).
The training should be done by you. If needed, we can provide AWS instances. However, please remember that GPUs available on AWS don't have enough memory for recent networks such as VGG.
Please avoid generic bids. In order to show that you have read and understood this text, please start you bid with “Deep learning projet”. Please explain what library you intend to use. If you think you can do 2- and 3- together, please explain how, this will be still better. This is urgent, we will make a decision in the next 2-3 days.
Deep learning projet
Hello.
I have a Msc degree in AI and have worked on a lot of projects like this.
I have worked with TensorFlow and can use it to train a model. Also we can use fusion algorithms to combine 2,3.
For programming language, I prefer to use Python.
Please let me know if you are interested and lets talk about the details.
Thanks,
Helmot
Deep learning projet
Dear Sir or Madam.
I am professional Researcher in Data Mining, Computational Intelligence and Control Theory, based in Germany.
For further details please contact me.
Data learning project
I have completed my MS in Electrical Engineering and working in the field of designing for last 3 years. My projects have won more then 10 national level competitions. Area of Expertise -Discrete Time Signal Processing -Statistical Signal Processing -Adaptive Signal Processing -Random/Stochastic Processes -Spectral Estimation -Artifical Intelligence -Pattern Recognition -Wireless Communication -Computational Mathematics
I work full time as computer vision research engineer. I have worked with many classification, clustering, authentication, detection and many other computer vision projects. I can guarantee you a business-driven work with professionality and date-respected.
Absolutely, the 2 & 3 phase will be merged together. Thus due to the nature of Deep Learning concepts. Since CNN (what Deep learning uses inside) are made to decrease the level of complexity of defining your data and its features, Merging the two steps into one classification stage will result in better results and more time efficiency.
The first step, I will do or in C++ since I am fluent in it. However, if you insist to accomplish it in a scripting language, I have no problem.
Deep learning projet
Hi,
I am a Bioinformatician with a PhD in Bioinformatics and an Msc in Computer science.
I have worked with genomic data analysis for a long time especializing in machine learning and other statistical tools.
I am very comfortable in R and python so if you wish I can use the tensorflow method. I will admit that though i have a lot of exeperience with other statistical tools, I have not played around too much with deep learning and that is why I am interested in doing this project. I do know of a few commonly used pacakged in R like H2o and have played around wih it.
I only take very selective project and I am very thorough in what I do. Please let me know if you have more questions.
Hena
Dear Client, Greetings from Flowgica technologies,
I have experience with these skills. We do have similar experience doing something similar to yours therefore I am looking forward to discuss and move ahead.
please check our freelancer portfolio at https://www.freelancer.com/u/mmadi.html?page=portfolio
I am ready to work with you,kindly waiting for your response.
Thanks & Regards,
Mmadi
Though I am new to this freelancer, but I have done the machine learning part for recommendation system using MAHOUT , SPARK, NEO4J. In that I had trained the data using collaborative filtering , Linear regression for prediction.
For this solution ,
1--> I will start with segregation the conceptual keywords from others using Entity extraction algo in NLP.
For 2 and 3 we can use algorithms like Linear regression,Clustering or many more depends on the accuracy