geohot / ai-notebooks Goto Github PK

can anyone help me understand why this is resulting in a file not found error, trying to fetch the datasets from the mnist dataset to follow along with someone else doing the same thing, on their end this exact code works fine.

def fetch(url):
import requests, gzip, os, hashlib, numpy
fp = os.path.join("/tmp", hashlib.md5(url.encode('utf-8')).hexdigest())
if not os.path.isfile(fp):
with open(fp, "rb") as f:
dat = f.read()
else:
with open(fp, "wb") as f:
dat = requests.get(url).content
f.write(dat)
return numpy.frombuffer(gzip.decompress(dat), dtype=np.uint8).copy()
X_train = fetch("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz")[0x10:].reshape((-1, 28, 28))
Y_train = fetch("http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz")[8:]
X_test = fetch("http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz")[0x10:].reshape((-1, 28, 28))
Y_test = fetch("http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz")[8:]

in fetch(url)
6 print(fp)
7 if not os.path.isfile(fp):
----> 8 with open(fp, "rb") as f:
9 dat = f.read()
10 else:

FileNotFoundError: [Errno 2] No such file or directory: '/tmp/23278f029ff68f1e993776e500ce06b9'

you might find this interesting... a lossless compression method: https://arxiv.org/pdf/1712.00012.pdf
I could not follow it very well on first attempt. If you struggle, this one helped me: https://arxiv.org/pdf/astro-ph/9603021.pdf

Hey George!

I've been currently learning CycleGAN. I would really appreciate if you can write a simple notebook with a sample example for the same. Since, you said as per the Readme!

Build a Reinforcement Learning Agent for Chess

Google recently released a paper on Reformer to increase performance of the Transformer self-attention NN model. Future State Of The Art CV models will be implemented on this architecture.

Prove that you can do it first.