When we consider performance, it is skill that speaks louder. We must have some special skills to be able to carry out the real work. I plan to list the things that we need to know to move this idea and project forward. Maybe my list is incomplete at the beginning, but I will try to complete it little by little.
2023/11/29
So far, we have been able to advance the work of collecting images for training. While working, we should be aware of choosing general categories. With the reviews we had, we came to the conclusion to choose the categories from general to detailed. So far, we have reached 6 general categories that we are gradually completing. We will try not to increase their number to more than 10 categories and instead of adding to the general categories, we will convert them into parent categories.
2023/10/31
Choosing a programming language that can meet the needs of ideas and projects is a sensitive and relatively difficult task. The variety of programming languages with many features that each language offers also makes this choice more difficult. We have to choose a language that is as much as possible higher than other languages.
2023/10/14
One of the ways to access the data set so that we can optimize the model method is Data Scraping. The data scraping technique allows us to collect the desired data from the Internet and various websites. In the Inchiyeh project, we need a large number of labeled images in different classes to get the best model result.
2023/10/05
In order to optimize and develop the desired model for Inchiyeh, we must find the proper dataset. So first, we need to know exactly what features the database we need has and what its structure should be. We make these features based on the performance we are considering.
2023/09/26
In the previous post, we mentioned that datasets are a collection of data. When we discuss collections, we conclude from this definition that the type of data itself can determine the classification of the dataset to a large extent. One of the benefits of this separation is adding new data to the relevant category. Every library or institution (Google Dataset Search, Kaggle, Amazon, Github, etc.) that has been active in this field has provided different categories, but in this article we want to review some of the most important ones.
2023/09/23
Another challenge that we expected to meet along the way is the challenge or rather the super challenge of the Data set. Datasets are a collection of data that are used in the machine learning process. Each sample in the dataset is independent from other samples and the columns of the dataset show special characteristics. Data sets really play an important role in the discussion of machine learning and the development of intelligent systems. Actually, the machine learns what the data gives it.
2023/09/19
Until today, we have passed the most difficult step, the beginning. Now we are moving forward with the plans we made before. Accordingly, we needed a series of tools, including a blog, task management, social pages, GitHub, and functional scripts, which we will discuss further.
2023/09/19
You get the idea from the name. You are going to send a picture of anything that you could not identify and understand what it is so that Inchiyeh will tell you what it is. So far, the general and hidden idea behind Inchiyeh.ir has been revealed. From a technical point of view, it can be said that we are developing a model for image classification. We will develop and train a model that can classify the image sent by the users into different classes.
2023/09/19
I think we all agree that starting anything is the hardest part of it. Why? Because it has its own difficulties. You don't even know where to start. Sometimes you don't even know if you should start or not. After about three or four years of thinking and many discussions, we finally decided to start...
2023/09/17