Skip to content

Instantly share code, notes, and snippets.

View mil-ad's full-sized avatar
🍉
Focusing

Milad Alizadeh mil-ad

🍉
Focusing
View GitHub Profile
@mil-ad
mil-ad / train-cifar.py
Created January 10, 2020 19:09 — forked from y0ast/train_cifar.py
Getting a high accuracy on CIFAR-10 is not straightforward. This self-contained script gets to 94% accuracy with a minimal setup.
import argparse
from tqdm import tqdm
import torch
import torch.nn.functional as F
from torchvision import models, datasets, transforms
def get_CIFAR10(root="./"):

Keybase proof

I hereby claim:

  • I am mi-lad on github.
  • I am notmilad (https://keybase.io/notmilad) on keybase.
  • I have a public key ASDZDChDJrc5mS2-PlwK65DSq-fEZiUWCjGWwLNPgNSmfAo

To claim this, I am signing this object:

Text Styles

B - Bold

I - Italic

U - Underline

E - Strikethrough