Day 0: Preparation day
This journey started when I received the "You have been accepted into the Secure and Private AI Scholarship Challenge Program" email.
One of the challenge in this project is to code in 60 days. My project would be Jar Classification Machine. Let us see if I can manage to implement further up to a mobile application. The project is similar to dog and cat classification. But this time, I want to classify the jars according to its model and brand. My dream is to have a visual scanner mobile app, a kind of barcode reader but this time just by take the photo of a jar. Why it is a dream, because I don't think I can manage to finish by having a fully working mobile app. I just want to take a step by step to achieve that, it may take more than 60 days, but I do not care. The progress is the important thing.
Today is preparation day. First I setup this blog to record all activities. I chose blogspot for the sake of simplicity. In just few minutes it can be run. I understand other blogging platform like wordpress is also simple. But, I would use them in other projects.
Second, I would like to try to run the dog classification project locally. I see this as the base code for the jar classification. First objective is to run dog classification project locally using jupyter notebook. I followed instruction from Lesson 3 : 7 Notebook Exercise Instructions. Be careful. I got into problem when following the instructions since the steps instructions were not including the pytorch installation. Below were instructions I used to run the dog classification project.
# Create conda environment, name it pysyft and use python 3 and activate it
Third, I took some jar photos. First problem is the number of photos for each jar to be taken. I asked this question on the slack channel but unfirtunately, it is not showing anymore since the messages was over 10,000. One said 16 was the minimum and other person said to use cv library to take a lot of pictures. At this moment, I only took minimum 4 for some jars and up to 8 for the rest. I took very small number of pictures since some jars are cylinder and in every corners will look the same. What I am missing probably, shoots from above and below and if possible to use different background. Does it make sense?
One of the challenge in this project is to code in 60 days. My project would be Jar Classification Machine. Let us see if I can manage to implement further up to a mobile application. The project is similar to dog and cat classification. But this time, I want to classify the jars according to its model and brand. My dream is to have a visual scanner mobile app, a kind of barcode reader but this time just by take the photo of a jar. Why it is a dream, because I don't think I can manage to finish by having a fully working mobile app. I just want to take a step by step to achieve that, it may take more than 60 days, but I do not care. The progress is the important thing.
Today is preparation day. First I setup this blog to record all activities. I chose blogspot for the sake of simplicity. In just few minutes it can be run. I understand other blogging platform like wordpress is also simple. But, I would use them in other projects.
Second, I would like to try to run the dog classification project locally. I see this as the base code for the jar classification. First objective is to run dog classification project locally using jupyter notebook. I followed instruction from Lesson 3 : 7 Notebook Exercise Instructions. Be careful. I got into problem when following the instructions since the steps instructions were not including the pytorch installation. Below were instructions I used to run the dog classification project.
# Create conda environment, name it pysyft and use python 3 and activate it
conda create -n pysyft python=3
conda activate pysyftconda install jupyter notebook
# Install pytorch, this is optional step, skip if pytorch is installed. [this step is not in the Lesson 3 : 7 Notebook Exercise Instructions, but taken from here.]conda install PyTorch -c PyTorch pip install torchvision# Install syft and numpy. Definition of pysyft from pypi, PySyft is a Python library for secure, private Deep Learning. PySyft decouples private data from model training, using Multi-Party Computation (MPC) within PyTorch. While from numpy, NumPy is the fundamental package for scientific computing with Python.
pip install syft
pip install numpy
Third, I took some jar photos. First problem is the number of photos for each jar to be taken. I asked this question on the slack channel but unfirtunately, it is not showing anymore since the messages was over 10,000. One said 16 was the minimum and other person said to use cv library to take a lot of pictures. At this moment, I only took minimum 4 for some jars and up to 8 for the rest. I took very small number of pictures since some jars are cylinder and in every corners will look the same. What I am missing probably, shoots from above and below and if possible to use different background. Does it make sense?
Comments
Post a Comment