publish [GPU]: course_UvA-DL/11-vision-transformer

Author: Azure Pipelines

.notebooks/course_UvA-DL/11-vision-transformer.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99d3e5c0387a867b8786f92aa292b6077cfe38a073ecace4b6bd4a7d3b40cca
+size 421917

.notebooks/course_UvA-DL/11-vision-transformer.jpg

@@ -0,0 +1,53 @@
+title: 'Tutorial 11: Vision Transformers'
+author: Phillip Lippe
+created: 2021-08-21
+updated: 2023-03-14
+license: CC BY-SA
+description: 'In this tutorial, we will take a closer look at a recent new trend:
+  Transformers for Computer Vision.
+
+  Since [Alexey Dosovitskiy et al.](https://openreview.net/pdf?id=YicbFdNTTy) successfully
+  applied a Transformer on a variety of image recognition benchmarks, there have been
+  an incredible amount of follow-up works showing that CNNs might not be optimal architecture
+  for Computer Vision anymore.
+
+  But how do Vision Transformers work exactly, and what benefits and drawbacks do
+  they offer in contrast to CNNs?
+
+  We will answer these questions by implementing a Vision Transformer ourselves, and
+  train it on the popular, small dataset CIFAR10.
+
+  We will compare these results to popular convolutional architectures such as Inception,
+  ResNet and DenseNet.
+
+  This notebook is part of a lecture series on Deep Learning at the University of
+  Amsterdam.
+
+  The full list of tutorials can be found at https://uvadlc-notebooks.rtfd.io.
+
+  '
+tags:
+- Image
+requirements:
+- torchvision
+- matplotlib
+- seaborn
+- lightning>=2.0.0
+- tensorboard
+accelerator:
+- CPU
+- GPU
+environment:
+- torch==2.0.1
+- torchmetrics==1.2.1
+- torchvision==0.15.2
+- pytorch-lightning==2.0.9.post0
+- matplotlib==3.8.4
+- ipython==8.16.1
+- seaborn==0.13.2
+- lightning==2.3.3
+- tensorboard==2.17.0
+- numpy==1.26.4
+- urllib3==2.2.2
+- setuptools==69.0.3
+published: '2024-07-19T20:16:19.153871'