VGG19 and VGG16 on Tensorflow.
machrisaa/tensorflow-vgg is ranked 8,828 with 2,236 stars.
Same-category comparison
machrisaa/tensorflow-vgg is ranked 8,828 among these 8 peers; lonePatient/BERT-NER-Pytorch is ranked 8,827.
Same-category comparison| Name | Rank | Metrics |
|---|
| Accenture/AmpliGraph | 8,821 | - Language:
- Python
- Stars:
- 2,242
- Forks:
- 257
- Description:
- Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org.
|
|---|
| Daniil-Osokin/lightweight-human-pose-estimation.pytorch | 8,825 | - Language:
- Python
- Stars:
- 2,236
- Forks:
- 494
- Description:
- Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
|
|---|
| KaiyangZhou/CoOp | 8,826 | - Language:
- Python
- Stars:
- 2,236
- Forks:
- 233
- Description:
- Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22).
|
|---|
| lonePatient/BERT-NER-Pytorch | 8,827 | - Language:
- Python
- Stars:
- 2,236
- Forks:
- 432
- Description:
- Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span).
|
|---|
| ahmedfgad/GeneticAlgorithmPython | 8,832 | - Language:
- Python
- Stars:
- 2,232
- Forks:
- 500
- Description:
- Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).
|
|---|
| thuml/iTransformer | 8,833 | - Language:
- Python
- Stars:
- 2,231
- Forks:
- 374
- Description:
- Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight).
|
|---|
| WillKoehrsen/feature-selector | 8,838 | - Language:
- Jupyter Notebook
- Stars:
- 2,228
- Forks:
- 760
- Description:
- Feature selector is a tool for dimensionality reduction of machine learning datasets.
|
|---|
| XLabs-AI/x-flux | 8,839 | - Language:
- Python
- Stars:
- 2,228
- Forks:
- 156
|
|---|
Key parameters and specifications
Key parameters and specifications| Parameter | Value |
|---|
| Language | Python |
|---|
| Category | Model Development |
|---|
| Subcategory | Architecture |
|---|
| Stars | 2,236 |
|---|
| Forks | 1,049 |
|---|
| Contributors | 6 |
|---|
| Created date | 2016-03-16 |
|---|
| Updated date | 2026-10-15 |
|---|
| Stars in 1 day | 0 |
|---|
| Stars in 7 days | 1 |
|---|
| Rank | 8,828 |
|---|
| Previous rank | 5,297 |
|---|
| Rank change | -3,531 |
|---|
| 7-day stars rank | 9,440 |
|---|
| Previous 7-day stars rank | 9,491 |
|---|
| 7-day stars rank change | 51 |
|---|
| Total stars rank | 5,800 |
|---|
| Previous total stars rank | 5,793 |
|---|
| Total stars rank change | -7 |
|---|
README summary
Tensorflow VGG16 and VGG19 This is a Tensorflow implemention of VGG 16 and VGG 19 based on tensorflow-vgg16 and Caffe to Tensorflow. Original Caffe implementation can be found in here and here. We have modified the implementation of tensorflow-vgg16 to use numpy loading instead of default tensorflow model loading in order to speed up the initialisation and reduce the overall memory usage. This implementation enable further modify the network, e. remove the FC layers, or increase the batch
size. >To use the VGG networks, the npy files for VGG16 NPY or VGG19 NPY has to be downloaded. Usage Use this to build the VGG object or The is a tensor with shape . All the VGG layers (tensors) can then be accessed using the vgg object. Extra This library has been used in my another Tensorflow image style synethesis project: stylenet Update 1: Trainable VGG: Added a trainable version of the VGG19 . It support train from existing vaiables or
from scratch. (But the trainer is not included) A very simple testing is added , switch has demo about how to train, switch off train mode for verification, and how to save. A seperated file is added (instead of changing existing one) because I want to keep the simplicity of the original VGG networks. 0: All the source code has been upgraded to v1. The conversion is done by my another project tf0to1
Frequently asked questions
How many stars and forks are recorded?
machrisaa/tensorflow-vgg has 2,236 stars and 1,049 forks.
What is the repository rank?
machrisaa/tensorflow-vgg is ranked 8,828.
What language and category are recorded?
machrisaa/tensorflow-vgg has 2,236 stars, uses Python and belongs to Model Development.
Which repository is closest in rank?
machrisaa/tensorflow-vgg is compared with lonePatient/BERT-NER-Pytorch, ranked 8,827 with 2,236 stars.
Tensorflow VGG16 and VGG19
This is a Tensorflow implemention of VGG 16 and VGG 19 based on tensorflow-vgg16 and Caffe to Tensorflow. Original Caffe implementation can be found in here and here.
We have modified the implementation of tensorflow-vgg16 to use numpy loading instead of default tensorflow model loading in order to speed up the initialisation and reduce the overall memory usage. This implementation enable further modify the network, e.g. remove the FC layers, or increase the batch size.
To use the VGG networks, the npy files for VGG16 NPY or VGG19 NPY has to be downloaded.
Usage
Use this to build the VGG object
vgg = vgg19.Vgg19()
vgg.build(images)
or
vgg = vgg16.Vgg16()
vgg.build(images)
The images is a tensor with shape [None, 224, 224, 3].
Trick: the tensor can be a placeholder, a variable or even a constant.
All the VGG layers (tensors) can then be accessed using the vgg object. For example, vgg.conv1_1, vgg.conv1_2, vgg.pool5, vgg.prob, ...
test_vgg16.py and test_vgg19.py contain the sample usage.
Extra
This library has been used in my another Tensorflow image style synethesis project: stylenet
Update 1: Trainable VGG:
Added a trainable version of the VGG19 vgg19_trainable. It support train from existing vaiables or from scratch. (But the trainer is not included)
A very simple testing is added test_vgg19_trainable, switch has demo about how to train, switch off train mode for verification, and how to save.
A seperated file is added (instead of changing existing one) because I want to keep the simplicity of the original VGG networks.
Update 2: Tensorflow v1.0.0:
All the source code has been upgraded to v1.0.0.
The conversion is done by my another project tf0to1