Skip to main content

DnnLab

Project description

DnnLab

Dnnlab is a small framework for deep learning models based on TensorFlow.

It provides custom training loops for:

  • Generative Models (GAN, cGan, cycleGAN)
  • Image Detection (custom YOLO)

Additonaly custom Keras Layer:

  • Non-Local-Blocks (Self-Attention)
  • Squeeze and Excitation Blocks (SEBlocks)
  • YOLO-Decoding Layer

Input pipeline functionality:

  • YOLO (Tfrecords to Datasets)
  • YOLO data augmentation
  • Generative Models (Tfrecords to Datasets)

TensorBoard output:

  • YOLO coco metrics (Precision (mAP) & Recall)
  • YOLO loss (loss_class, loss_conf, loss_xywh, total_loss)
  • YOLO bounding boxes
  • Generative Models (Loss & Images)

Requirements

TensorFlow 2.3.0

Installation

Run the following to install:

pip install dnnlab

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

dnnlab-2.2.5.tar.gz (80.7 kB view hashes)

Uploaded Source

Built Distribution

dnnlab-2.2.5-py3-none-any.whl (118.9 kB view hashes)

Uploaded Python 3

Supported by

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