Skip to main content

A PyTorch based software platform for teaching the Deep Learning class at Purdue University

Project description

Consult the module API page at

https://engineering.purdue.edu/kak/distDLS/DLStudio-2.5.5.html

for all information related to this module, including the information about the latest changes to the code.

convo_layers_config = "1x[128,3,3,1]-MaxPool(2) 1x[16,5,5,1]-MaxPool(2)"
fc_layers_config = [-1,1024,10]

dls = DLStudio(
                  dataroot = "/home/kak/ImageDatasets/CIFAR-10/",
                  image_size = [32,32],
                  convo_layers_config = convo_layers_config,
                  fc_layers_config = fc_layers_config,
                  path_saved_model = "./saved_model",
                  momentum = 0.9,
                  learning_rate = 1e-3,
                  epochs = 2,
                  batch_size = 4,
                  classes = ('plane','car','bird','cat','deer','dog','frog','horse','ship','truck'),
                  use_gpu = True,
                  debug_train = 0,
                  debug_test = 1
              )

configs_for_all_convo_layers = dls.parse_config_string_for_convo_layers()
convo_layers = dls.build_convo_layers2( configs_for_all_convo_layers )
fc_layers = dls.build_fc_layers()
model = dls.Net(convo_layers, fc_layers)
dls.show_network_summary(model)
dls.load_cifar_10_dataset()
dls.run_code_for_training(model)
dls.run_code_for_testing(model)

Project details


Download files

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

Source Distribution

DLStudio-2.5.5.tar.gz (414.2 kB view details)

Uploaded Source

File details

Details for the file DLStudio-2.5.5.tar.gz.

File metadata

  • Download URL: DLStudio-2.5.5.tar.gz
  • Upload date:
  • Size: 414.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for DLStudio-2.5.5.tar.gz
Algorithm Hash digest
SHA256 c67ec5005e4eb04a248a95c115442211decfb4b8a9ab704625a6d16a890d155a
MD5 99189711cade230202de6c1086cda0e1
BLAKE2b-256 6ed3314377688819089aabb7c6479c6941ec1b436d4e588ecaf4de1e2d100a3c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page