Topics (202k) Articles (203k) Users (297) Discussions (237) Comments (383) Files (715) New article
They can't even make this basic stuff just work!
By default, the setup runs on CPU only, not GPU, as could be seen by running htop. But by the magic of PyTorch, modifying the program to run on the GPU is trivial:and leads to a faster runtime, with less
cat << EOF | patch
diff --git a/run.py b/run.py
index 104d363..20072d1 100644
--- a/run.py
+++ b/run.py
@@ -24,7 +24,8 @@ data_test = MNIST('./data/mnist',
data_train_loader = DataLoader(data_train, batch_size=256, shuffle=True, num_workers=8)
data_test_loader = DataLoader(data_test, batch_size=1024, num_workers=8)
-net = LeNet5()
+device = 'cuda'
+net = LeNet5().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=2e-3)
@@ -43,6 +44,8 @@ def train(epoch):
net.train()
loss_list, batch_list = [], []
for i, (images, labels) in enumerate(data_train_loader):
+ labels = labels.to(device)
+ images = images.to(device)
optimizer.zero_grad()
output = net(images)
@@ -71,6 +74,8 @@ def test():
total_correct = 0
avg_loss = 0.0
for i, (images, labels) in enumerate(data_test_loader):
+ labels = labels.to(device)
+ images = images.to(device)
output = net(images)
avg_loss += criterion(output, labels).sum()
pred = output.detach().max(1)[1]
@@ -84,7 +89,7 @@ def train_and_test(epoch):
train(epoch)
test()
- dummy_input = torch.randn(1, 1, 32, 32, requires_grad=True)
+ dummy_input = torch.randn(1, 1, 32, 32, requires_grad=True).to(device)
torch.onnx.export(net, dummy_input, "lenet.onnx")
onnx_model = onnx.load("lenet.onnx")
EOFuser as now we are spending more time on the GPU than CPU:real 1m27.829s
user 4m37.266s
sys 0m27.562s
Note that:
- the images must be drawn with white on black. If you use black on white, it the accuracy becomes terrible. This is a good very example of brittleness in AI systems!
- images must be converted to 32x32 for
lenet.onnx, as that is what training was done on. The training step converted the 28x28 images to 32x32 as the first thing it does before training even starts
We can try the code adapted from thenewstack.io/tutorial-using-a-pre-trained-onnx-model-for-inferencing/ at lenet/infer.py:and it works pretty well! The program outputs:as desired.
cd lenet
cp ~/git/LeNet-5/lenet.onnx .
wget -O 9.png https://raw.githubusercontent.com/cirosantilli/media/master/Digit_9_hand_drawn_by_Ciro_Santilli_on_GIMP_with_mouse_white_on_black.png
./infer.py 9.png9We can also try with images directly from Extract MNIST images.and the accuracy is great as expected.
infer_mnist.py lenet.onnx mnist_png/out/testing/1/*.pngThey actually have two The Oxford Student and Cherwell. As brilliantly highlighted in this first of April piece:
Related:
- www.thestudentroom.co.uk/showthread.php?t=1167619 "OxStu vs. Cherwell"
E.g.: thecollegestore.co.uk/products/ladies-oxford-college-puffer-jacket?variant=40590030864549 Black with 5 rows, on left chest "colege name", logo, "Oxford", and right chest optional initials (or sometimes other identifiers/nicknames) to help distinguish from all the other people's identical clothes.
This has a whitelabel version: www.workweargiant.co.uk/product/result-urban-holkham-down-feel-jacket/, the name appears to be "Holkham Down Feel Jacket".
If you look 20 and wear one of those, it's almost an ID, you can get anywhere that does not require a key card, porters won't look at you twice!
- www.oxfordstudent.com/2019/03/25/in-opposition-to-stash/ In opposition to stash by Morgan Jones (2019), basically because university is your last chance to wear what you want on many professions.
Bibliography:
Like the U.S.' summer term.
E-learning system prior to Canvas: weblearn.ox.ac.uk/portal. Appears fully custom and closed source?
Like the U.S.' spring term.
Version of TensorFlow with a Cirq backend that can run in either quantum computers or classical computer simulations, with the goal of potentially speeding up deep learning applications on a quantum computer some day.
Basic example tested on SQLite 3.40.1, Ubuntu 23.04:output:
sqlite3 :memory: 'select 1 union select 2'1
2Two columns two rows:output:
sqlite3 :memory: <<EOF
select * from (values (1, 2), (2, 3))
union
select * from (values (2, 3), (3, 4))
EOF1|2
2|3
3|4Note how duplicates are removed, to keep them we output:
UNION ALL instead:sqlite3 :memory: <<EOF
select * from (values (1, 2), (2, 3))
union all
select * from (values (2, 3), (3, 4))
EOF1|2
2|3
2|3
3|4 Pinned article: Introduction to the OurBigBook Project
Welcome to the OurBigBook Project! Our goal is to create the perfect publishing platform for STEM subjects, and get university-level students to write the best free STEM tutorials ever.
Everyone is welcome to create an account and play with the site: ourbigbook.com/go/register. We belive that students themselves can write amazing tutorials, but teachers are welcome too. You can write about anything you want, it doesn't have to be STEM or even educational. Silly test content is very welcome and you won't be penalized in any way. Just keep it legal!
Intro to OurBigBook
. Source. We have two killer features:
- topics: topics group articles by different users with the same title, e.g. here is the topic for the "Fundamental Theorem of Calculus" ourbigbook.com/go/topic/fundamental-theorem-of-calculusArticles of different users are sorted by upvote within each article page. This feature is a bit like:
- a Wikipedia where each user can have their own version of each article
- a Q&A website like Stack Overflow, where multiple people can give their views on a given topic, and the best ones are sorted by upvote. Except you don't need to wait for someone to ask first, and any topic goes, no matter how narrow or broad
This feature makes it possible for readers to find better explanations of any topic created by other writers. And it allows writers to create an explanation in a place that readers might actually find it.
Figure 1. Screenshot of the "Derivative" topic page. View it live at: ourbigbook.com/go/topic/derivativeVideo 2. OurBigBook Web topics demo. Source. - local editing: you can store all your personal knowledge base content locally in a plaintext markup format that can be edited locally and published either:This way you can be sure that even if OurBigBook.com were to go down one day (which we have no plans to do as it is quite cheap to host!), your content will still be perfectly readable as a static site.
- to OurBigBook.com to get awesome multi-user features like topics and likes
- as HTML files to a static website, which you can host yourself for free on many external providers like GitHub Pages, and remain in full control
Figure 2. You can publish local OurBigBook lightweight markup files to either OurBigBook.com or as a static website.
Figure 3. Visual Studio Code extension installation.
Figure 5. . You can also edit articles on the Web editor without installing anything locally. Video 3. Edit locally and publish demo. Source. This shows editing OurBigBook Markup and publishing it using the Visual Studio Code extension. 
- Infinitely deep tables of contents:
All our software is open source and hosted at: github.com/ourbigbook/ourbigbook
Further documentation can be found at: docs.ourbigbook.com
Feel free to reach our to us for any help or suggestions: docs.ourbigbook.com/#contact