a small classfication neural network framework
Project description
NN Framework For Dummies
A simple neural network framework that use similar interface to TensorFlow
#colab link
https://colab.research.google.com/drive/1uXPiYy5kjNvUR31bzw_IrnX4zRJ6G3Wx?usp=sharing
Installation
$ pip install nn-for-dummies
Usage
model = nn.Model(
nn.Layer(size=(4,5), activation='Relu'),
nn.Layer(size=(5,3), activation='Relu'),
nn.Layer(size=(3,10), activation='sigmoid'),
nn.Layer(size=(10,6), activation='ReLU'),
nn.Layer(size=(6,1), activation='ReLU')
)
# import and preprocess data
x,label = Data.get_data("data_banknote_authentication.csv")
x = Data.normalize(x)
X_train, X_test, label_train, label_test = Data.split_data(x,label)
# Train the model
model.fit(X_train,label_train,'SGD','MSE',alpha = 0.0001,epoch = 15,graph_on = True)
# evaluate the model
[accuracy,f1_score,confusion_matrix] = model.evaluate(X_test,label_test,metric = ['accuracy','f1 score','confusion matrix'])
print(f"accuracy: {accuracy}")
print(f"f1_score: {f1_score}")
print("confusion matrix:\n",confusion_matrix)
model.save()
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nn_for_dummies-0.0.42.tar.gz
(10.0 kB
view hashes)
Built Distribution
Close
Hashes for nn_for_dummies-0.0.42-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c89f2bab5970c6d2227206b73b48a052368d6dcae83d9c10a1fe27219410866e |
|
MD5 | 5a4bcb5335884382ef7a6d84bbed94d2 |
|
BLAKE2b-256 | d9c17a1bcccaeeff2f2c430923a1423672c70f97a3c2b5950826a9ff56310635 |