Using the board shown in figure 3, the tool generated these boards: Now, let’s look at the concept of data augmentation. Then in figure 2, we see there are two gaps on this board.įinally, in figure 3, the gaps are converted into occupied fields. Well, while testing the model, I found it was more cost-effective to ignore all the gaps than leaving them on the boards.įigure 1 shows an original 20×10 board scraped from the video. So I made the Tetris Data Augmentation tool to artificially expand the dataset by creating modified versions of the original boards.īut before processing, I changed all boards by converting all gaps into occupied fields. I estimated that I needed at least 1,000,000 records. Unfortunately, 50,000 data records were not enough to train the network. Using this tool, I processed 15 Tetris World Championship matches, generating around 50,000 useful records.
This way, it recognizes the current board configuration and the position of the currently played tetromino. So I made Tetris Data Scraper, a specific tool that collects data from videos of Tetris matches:īased on the image processing of each video frame, this tool analyzes differences between pixel colors of the previous and current frames. And that was my original idea of getting the training data. So these matches are a great resource of high-quality Tetris data! You only have to scrape it somehow. Besides, they aim to score the most points by clearing four rows at once all the time. There, all competitors play Tetris at the top level producing a small number of errors. Well, there is Youtube channel with a lot of videos showing Tetris World Championship matches. the label is an action that represents the final column placement and rotation of a played piece on that board.To train the network, I needed a high-quality dataset of the various board configurations described by images with corresponding labels where:
0 kommentar(er)
