Python program
- or -
Post a project like this1370
£250(approx. $314)
- Posted:
- Proposals: 11
- Remote
- #2867542
- Awarded
WordPress Expert/Woocommerce Expert/Data Scientist/Python Expert/Auto-CAD/3D/2D Animation/ White Board Animation
Rawalpindi
Administration, Data Science, Robotics, Deep Learning, Machine Learning, Computer Vision
Kazan
Website Developer, Graphic Designer, Transcriber, Content writer, CAD Expert, Python Developer, Photo Editor, Web Scrapper, JAVA developer, Android developer, Wix/Shopify Expert,
Regensburg
3151005436479100775624990062543778374971238168294139655436384843701634396461
Description
Experience Level: Expert
I would like to have a Python project done along with a report discussing the findings and explanations of the work performed. Below you can view the relevant instructions. I would like you to do 4 out of the 5 requirements.
INSTRUCTIONS
Get faceRec.py (file is attached) run it in Python. (The first time you run it, it downloads a large data set of face images from the internet, which requires several hundred MBs of free hard disk space. If you get an error message related to a function „urllib.urlretrieve“, this is likely caused by connectivity problems, so try again several hours later).
Modify faceRec.py in a number of different ways, and write a report containing descriptions of your methods and results:
1. Replace the learner in the original program (faceRec.py) with a multilayer Perceptron (having one hidden layer) using scikit-learn. In the report you MUST describe all parameters of the perceptron and training method, and how they were set. Also write about the accuracy of the resulting method.
2. Replace the learner in the original program (faceRec.py) with a deep convolutional neural network using the keras or TensorFlow library (do not use dimensionality reduction with this learner). In the report you MUST desrcibe all parameters of the neural network and training method, and how they were set. Also write about the accuracy of the resulting method.
3. Use methods from scikit-image to try and find the eyes in each picture of the data set (it may be easiest to select a random subset of suitable size and display them together with the inferred position of the eyes as images using matplotlib. Accuracy can then be reported by counting the number of correctly marked eyes.) In the report you MUST describe the method of detecting the eyes, and the resulting accuracy.
4. Use a clustering method of your choice to cluster the images, and measure how accurately the clusters correspond to the sets of images of one person. (You should not use dimensionality reduction methods like PCA for this task, but you may decrease the resolution of the images if you need to speed things up). You also need to investigate whether using one chosen image pre-processing method from scikit-learn can improve this accuracy. Create a subsection in the report where you mention your methods and the resulting accuracy.
5. Take a set of images of only two different persons. Apply PCA as in the original program. Then pass a suitable number of principal components to a genetic programming system that is implemented using the deap library, and evolve a function that outputs a positive number if an image is from one person, otherwise a negative number. Measure the accuracy of the evolved classifier. Create a subsection in your report where you describe your methods and results.
IMPORTANT THINGS
1. The report should have a brief introduction where you summarize what you did. It is not necessary to write a literature review. However, if you took a significant portion of code rom somewhere, you must reference it.
2. You must also reference any scientific paper or other source that you used for deciding which methods or parameters to use.
3. For this assignment, it should not normally be necessary to take significant portions of code from anywhere except the online documentation of the libraries used.
4. You must not use any direct file, system or web access methods in your code.
5. The code must be submitted in TWO forms: (a) all Python files, (b) the whole code from all files as an appendix to your report. Do NOT submit the report as compressed / zipped file --- please submit the original file format (DOC or PDF).
INSTRUCTIONS
Get faceRec.py (file is attached) run it in Python. (The first time you run it, it downloads a large data set of face images from the internet, which requires several hundred MBs of free hard disk space. If you get an error message related to a function „urllib.urlretrieve“, this is likely caused by connectivity problems, so try again several hours later).
Modify faceRec.py in a number of different ways, and write a report containing descriptions of your methods and results:
1. Replace the learner in the original program (faceRec.py) with a multilayer Perceptron (having one hidden layer) using scikit-learn. In the report you MUST describe all parameters of the perceptron and training method, and how they were set. Also write about the accuracy of the resulting method.
2. Replace the learner in the original program (faceRec.py) with a deep convolutional neural network using the keras or TensorFlow library (do not use dimensionality reduction with this learner). In the report you MUST desrcibe all parameters of the neural network and training method, and how they were set. Also write about the accuracy of the resulting method.
3. Use methods from scikit-image to try and find the eyes in each picture of the data set (it may be easiest to select a random subset of suitable size and display them together with the inferred position of the eyes as images using matplotlib. Accuracy can then be reported by counting the number of correctly marked eyes.) In the report you MUST describe the method of detecting the eyes, and the resulting accuracy.
4. Use a clustering method of your choice to cluster the images, and measure how accurately the clusters correspond to the sets of images of one person. (You should not use dimensionality reduction methods like PCA for this task, but you may decrease the resolution of the images if you need to speed things up). You also need to investigate whether using one chosen image pre-processing method from scikit-learn can improve this accuracy. Create a subsection in the report where you mention your methods and the resulting accuracy.
5. Take a set of images of only two different persons. Apply PCA as in the original program. Then pass a suitable number of principal components to a genetic programming system that is implemented using the deap library, and evolve a function that outputs a positive number if an image is from one person, otherwise a negative number. Measure the accuracy of the evolved classifier. Create a subsection in your report where you describe your methods and results.
IMPORTANT THINGS
1. The report should have a brief introduction where you summarize what you did. It is not necessary to write a literature review. However, if you took a significant portion of code rom somewhere, you must reference it.
2. You must also reference any scientific paper or other source that you used for deciding which methods or parameters to use.
3. For this assignment, it should not normally be necessary to take significant portions of code from anywhere except the online documentation of the libraries used.
4. You must not use any direct file, system or web access methods in your code.
5. The code must be submitted in TWO forms: (a) all Python files, (b) the whole code from all files as an appendix to your report. Do NOT submit the report as compressed / zipped file --- please submit the original file format (DOC or PDF).
Ad O.
100% (4)Projects Completed
4
Freelancers worked with
2
Projects awarded
50%
Last project
3 Sep 2020
United Kingdom
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies