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 py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page