Skip to main content

Convolutional Neural Netoworks Training Tools

Project description

convtt

Convolutional Neural Netoworks Training Tools

example of DenseNet training

The example is included in the bin folder in the package with the file name of convtt_train_densenet.py.

Here is a code snippet of creating a trainer and train the network given the model and the dataset.

# convtt_train_densenet.py
from convtt.models import densenet
from convtt.train.trainer import *

# initialise trainer
optimiser = build_optimiser(model=model, name='ScheduledSGD', milestones=[10, 20], lr=0.1)
driver = build_driver(model=model, training_epoch=30, batch_size=128, training_data=dataset.train['images'],
                      training_label=dataset.train['labels'],
                      validation_data=None, validation_label=None, test_data=dataset.test['images'],
                      test_label=dataset.test['labels'], optimiser=optimiser)
trainer = build_trainer(optimiser=optimiser, driver=driver)
test_acc = trainer.eval()
print(test_acc)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for convtt, version 0.0.2
Filename, size File type Python version Upload date Hashes
Filename, size convtt-0.0.2-py3-none-any.whl (42.2 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size convtt-0.0.2.tar.gz (27.3 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page