machrisaa/tensorflow-vgg

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2237 stars · 1050 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library implementing the VGG16 and VGG19 convolutional neural networks in TensorFlow, loading pretrained weights from npy files for fast initialization and lower memory usage. It exposes all network layers as accessible tensors and includes a trainable variant of VGG19.

Use cases

• extract features from images using pretrained VGG layers
• classify images with VGG16 or VGG19 in TensorFlow
• build a VGG network with custom batch size or removed FC layers
• fine-tune or train VGG19 from pretrained weights or scratch
• use VGG as a backbone for style transfer or other vision models

When to choose

• you need a simple, modifiable VGG implementation in TensorFlow with easy access to intermediate layers
• you want faster initialization and lower memory usage than default TensorFlow model loading
• you need a trainable VGG19 variant to fine-tune on your own data

When to avoid

• you are using TensorFlow 2.x or Keras, where built-in pretrained VGG applications are better maintained
• you need a license-protected or actively maintained project
• you require models beyond VGG16/VGG19 or modern architectures like ResNet or EfficientNet

Facets

library · maturity maintenance

machine-learning deep-learning deep-learning computer-vision image-processing python vgg16 vgg19 tensorflow pretrained-models image-classification convolutional-networks

Member repositories

For agents

markdown · JSON · MCP: product_card(name="machrisaa/tensorflow-vgg")