Eddie's Learning RecordsEddie's Learing Record 44
1. DurationMonday, Apr. 24th, 2023 - Sunday, Apr. 30th, 20232. Learning Records2.1. UpdatingRevised my English Curriculum Vitae and Chinese Resume bas...
Eddie's Learning RecordsEddie's Learning Record 23
1. Duration Monday, November 7th, 2022 - Saturday, November 12th, 2022 2. Learning Record 2.1 Give a Pitch to My Junior Fellow I supposed him to be a professor of deep learning, but he turned out to be a rookie. He even didn't finish the machine learning course. Luckily, he is interested in t...
Eddie's Learning RecordsEddie's Learning Record 40
Eddie's Learning RecordsEddie's Learing Record 44
1. DurationMonday, Apr. 24th, 2023 - Sunday, Apr. 30th, 20232. Learning Records2.1. UpdatingRevised my English Curriculum Vitae and Chinese Resume bas...
Eddie's Learning RecordsEddie's Learning Record 23
1. Duration Monday, November 7th, 2022 - Saturday, November 12th, 2022 2. Learning Record 2.1 Give a Pitch to My Junior Fellow I supposed him to be a professor of deep learning, but he turned out to be a rookie. He even didn't finish the machine learning course. Luckily, he is interested in t...
Eddie's Learning RecordsEddie's Learning Record 40
Share Dialog
Share Dialog
Subscribe to Eddie's Learning Records
Subscribe to Eddie's Learning Records
<100 subscribers
<100 subscribers
Monday, November 14th, 2022 - Saturday, November 19th, 2022
Fine-tuned the vision transformer model on the cat_and_dag dataset and the flowers dataset. The model achieved approximately 86% accuracy on the flowers dataset.
I also refactored the code for micro-expression spotting to fit the input shape of the vision transformer. But the result was as bad as shit. I needed time to fine-tune the hyperparameters.
I found a different structure of vision transformer called Swin Vit. I watched the video and planned to read the code the next week.
I read the paper [1] and refactored the code using TensorFlow to make its structure be similar to the vision transformer code shown in the d2l notebook.
The code worked well and gave a similar result on the cat_and_dog dataset and the flowers dataset.
I read the code carefully and found the SL-Vit changes the patch embedding and multilayer attention module of the vision transformer.
I don't have any good feelings even though the code ran well as I was blocked in my dorm for ten days.
[1]S. H. Lee, S. Lee, and B. C. Song, “Vision Transformer for Small-Size Datasets.” arXiv, 2021. doi: 10.48550/ARXIV.2112.13492.
Monday, November 14th, 2022 - Saturday, November 19th, 2022
Fine-tuned the vision transformer model on the cat_and_dag dataset and the flowers dataset. The model achieved approximately 86% accuracy on the flowers dataset.
I also refactored the code for micro-expression spotting to fit the input shape of the vision transformer. But the result was as bad as shit. I needed time to fine-tune the hyperparameters.
I found a different structure of vision transformer called Swin Vit. I watched the video and planned to read the code the next week.
I read the paper [1] and refactored the code using TensorFlow to make its structure be similar to the vision transformer code shown in the d2l notebook.
The code worked well and gave a similar result on the cat_and_dog dataset and the flowers dataset.
I read the code carefully and found the SL-Vit changes the patch embedding and multilayer attention module of the vision transformer.
I don't have any good feelings even though the code ran well as I was blocked in my dorm for ten days.
[1]S. H. Lee, S. Lee, and B. C. Song, “Vision Transformer for Small-Size Datasets.” arXiv, 2021. doi: 10.48550/ARXIV.2112.13492.
Eddie He
Eddie He
No activity yet