[PYTHON] real-time-Personal-estimation (What should I do to prevent the estimation of images outside the category) * Failure.

Articles up to the last time

Last time, yolov5 was learned to use GPU using a local machine. https://qiita.com/asmg07/items/0abad3e16886cb60ecef Here, as a test, we trained with epochs 1000 and the result was as follows. image.png As a result of testing based on this model, it turns out that learning is not done well as follows. Images outside the category image.png image.png Images in category image.png image.png The problem that can be seen from this result is that it is necessary to think about what to do in order to prevent the estimation of images outside the category.

Summary of this article

For the time being, I would like to actually try what happens if I increase the number of images to be learned from about 100 to hundreds or thousands.

Annotation

Since the image collection is shown above, I will omit it this time. The article is shown below. Search.py in the article https://qiita.com/asmg07/items/8502fe59b65f92d1e379 Vott is used for annotation. Image data ・ Asuka Saito 350 sheets ・ Yoda Yuki 350 sheets I'm thinking of going. In addition, leave only the images that can be used from the images downloaded by search.py and annotate from there You need to be patient here first because you will do.

About learning

epochs 50 times results.png

epochs 100 times results.png

Conclusion

Nogizaka recognition itself using yolo ended in failure. The reason is that it is excellent in recognizing people, but it is difficult to recognize individuals. I don't know why yet. So I will continue development using yolo, but the Nogizaka recognition project is on hold for the time being. Thank you very much.

Recommended Posts

real-time-Personal-estimation (What should I do to prevent the estimation of images outside the category) * Failure.
I want to visualize the transfer status of the 2020 J League, what should I do?
What to do when you get "I can't see the site !!!!"
What should I do with the Python directory structure after all?
What skills do I need to program with the FBX SDK Python?
What I did to keep track of the humidity and temperature of the archive
After all, what should I use to do type comparisons in Python?
Example of what to do when the sample script does not work (OpenCV-Python)
I failed when clustering with k-means, but what should I do (implementation of kernel k-means)
What to do if (base) is displayed at the beginning of the Mac terminal
[Python] What I did to do Unit Test
I tried to touch the API of ebay
I tried to correct the keystone of the image
What to do when PermissionError of tempfile.mkstemp occurs
I will summarize what I was happy to do to get out of the state where I do not know the letter D of Docker
What should I do with DICOM in MPEG2?
I want to customize the appearance of zabbix
I tried to predict the price of ETF
I tried to vectorize the lyrics of Hinatazaka46!
What to do if the progress bar is not displayed in tqdm of python
I want to grep the execution result of strace
I compared the identity of the images by Hu moment
I want to fully understand the basics of Bokeh
I tried to visualize the spacha information of VTuber
I tried to erase the negative part of Meros
What I did to ssh to the VPS Ubuntu environment
To do the equivalent of Ruby's ObjectSpace._id2ref in Python
I tried to classify the voices of voice actors
I want to increase the security of ssh connections
I tried to summarize the string operations of Python
The sound of tic disorder at work is ... I managed to do it with the code
Make a note of what you want to do in the future with Raspberry Pi
Ventilation is important. What I did to keep track of the C02 concentration in the room
What you should not do in the process of time series data analysis (including reflection)
I tried to find the trend of the number of ships in Tokyo Bay from satellite images.