16

GitHub - kaszperro/deepy

 5 years ago
source link: https://github.com/kaszperro/deepy
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

README.md

deepy

Deep learning library written in python just for fun.

It uses numpy for computations. API is similar to PyTorch's one.

Examples:

  • In examples directory there is a MNIST linear classifier, which scores over 96% accuracy.

  • Sequential model creation:

from deepy.module import Linear, Sequential
from deepy.autograd.activations import Softmax, ReLU
my_model = Sequential(
    Linear(28 * 28, 300),
    ReLU(),
    Linear(300, 300),
    ReLU(),
    Linear(300, 10),
    Softmax()
    )
  • Losses:
from deepy.module import Linear
from deepy.autograd.losses import CrossEntropyLoss, MSELoss
from deepy.variable import Variable
import numpy as np

my_model = Linear(10, 10)

loss1 = CrossEntropyLoss()
loss2 = MSELoss()


good_output = Variable(np.zeros((10,10)))
model_input = Variable(np.ones((10,10)))
model_output = my_model(model_input)

error = loss1(good_output, model_output)

# now you can propagate error backwards:
error.backward()
  • Optimizers:
from deepy.module import Linear
from deepy.autograd.losses import CrossEntropyLoss, MSELoss
from deepy.variable import Variable
from deepy.autograd.optimizers import SGD
import numpy as np


my_model = Linear(10, 10)

loss1 = CrossEntropyLoss()
loss2 = MSELoss()

optimizer1 = SGD(my_model.get_variables_list())

good_output = Variable(np.zeros((10,10)))
model_input = Variable(np.ones((10,10)))
model_output = my_model(model_input)

error = loss1(good_output, model_output)

# now you can propagate error backwards:
error.backward()

# and then optimizer can update variables:
optimizer1.zero_grad()
optimizer1.step()

report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK