ikhlestov / Vision_networks
Licence: mit
Repo about neural networks for images handling
Stars: ✭ 266
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Vision networks
yolov3-ios
Using yolo v3 object detection on ios platform.
Stars: ✭ 55 (-79.32%)
Mutual labels: densenet
densenet
A PyTorch Implementation of "Densely Connected Convolutional Networks"
Stars: ✭ 50 (-81.2%)
Mutual labels: densenet
chainer-DenseNet
Densely Connected Convolutional Network implementation by Chainer
Stars: ✭ 39 (-85.34%)
Mutual labels: densenet
TensorMONK
A collection of deep learning models (PyTorch implemtation)
Stars: ✭ 21 (-92.11%)
Mutual labels: densenet
DenseNet-human-pose-estimation
Using DenseNet for human pose estimation based on TensorFlow.
Stars: ✭ 34 (-87.22%)
Mutual labels: densenet
awesome-computer-vision-models
A list of popular deep learning models related to classification, segmentation and detection problems
Stars: ✭ 419 (+57.52%)
Mutual labels: densenet
3ddensenet.torch
3D DenseNet(torch version) for ModelNet40 dataset
Stars: ✭ 43 (-83.83%)
Mutual labels: densenet
gluon2pytorch
Gluon to PyTorch deep neural network model converter
Stars: ✭ 72 (-72.93%)
Mutual labels: densenet
deeplearning-mpo
Replace FC2, LeNet-5, VGG, Resnet, Densenet's full-connected layers with MPO
Stars: ✭ 26 (-90.23%)
Mutual labels: densenet
CNN-Series-Getting-Started-and-PyTorch-Implementation
我的笔记和Demo,包含分类,检测、分割、知识蒸馏。
Stars: ✭ 49 (-81.58%)
Mutual labels: densenet
speech-recognition-transfer-learning
Speech command recognition DenseNet transfer learning from UrbanSound8k in keras tensorflow
Stars: ✭ 18 (-93.23%)
Mutual labels: densenet
pytorch-SRDenseNet
Pytorch implementation for SRDenseNet (ICCV2017)
Stars: ✭ 70 (-73.68%)
Mutual labels: densenet
DenseNet-MURA-PyTorch
Implementation of DenseNet model on Standford's MURA dataset using PyTorch
Stars: ✭ 59 (-77.82%)
Mutual labels: densenet
pyro-vision
Computer vision library for wildfire detection
Stars: ✭ 33 (-87.59%)
Mutual labels: densenet
DenseNet-Cifar10
Train DenseNet on Cifar-10 based on Keras
Stars: ✭ 39 (-85.34%)
Mutual labels: densenet
DenseNet with TensorFlow
Two types of `Densely Connected Convolutional Networks <https://arxiv.org/abs/1608.06993>`__ (DenseNets) are available:
- DenseNet - without bottleneck layers
- DenseNet-BC - with bottleneck layers
Each model can be tested on such datasets:
- Cifar10
- Cifar10+ (with data augmentation)
- Cifar100
- Cifar100+ (with data augmentation)
- SVHN
A number of layers, blocks, growth rate, image normalization and other training params may be changed trough shell or inside the source code.
Example run:
.. code::
python run_dense_net.py --train --test --dataset=C10
List all available options:
.. code::
python run_dense_net.py --help
There are also many `other implementations <https://github.com/liuzhuang13/DenseNet>`__ - they may be useful also.
Citation:
.. code::
@article{Huang2016Densely,
author = {Huang, Gao and Liu, Zhuang and Weinberger, Kilian Q.},
title = {Densely Connected Convolutional Networks},
journal = {arXiv preprint arXiv:1608.06993},
year = {2016}
}
Test run
--------
Test results on various datasets. Image normalization per channels was used. Results reported in paper provided in parenthesis. For Cifar+ datasets image normalization was performed before augmentation. This may cause a little bit lower results than reported in paper.
====================== ====== =========== =========== ============== ==============
Model type Depth C10 C10+ C100 C100+
====================== ====== =========== =========== ============== ==============
DenseNet(*k* = 12) 40 6.67(7.00) 5.44(5.24) 27.44(27.55) 25.62(24.42)
DenseNet-BC(*k* = 12) 100 5.54(5.92) 4.87(4.51) 24.88(24.15) 22.85(22.27)
====================== ====== =========== =========== ============== ==============
Approximate training time for models on GeForce GTX TITAN X GM200 (12 GB memory):
- DenseNet(*k* = 12, *d* = 40) - 17 hrs
- DenseNet-BC(*k* = 12, *d* = 100) - 1 day 18 hrs
Difference compared to the `original <https://github.com/liuzhuang13/DenseNet>`__ implementation
---------------------------------------------------------
The existing model should use identical hyperparameters to the original code. If you note some errors - please open an issue.
Also it may be useful to check my blog post `Notes on the implementation DenseNet in tensorflow. <https://medium.com/@illarionkhlestov/notes-on-the-implementation-densenet-in-tensorflow-beeda9dd1504#.55qu3tfqm>`__
Dependencies
------------
- Model was tested with Python 3.4.3+ and Python 3.5.2 with and without CUDA.
- Model should work as expected with TensorFlow >= 0.10. Tensorflow 1.0 support was recently included.
Repo supported with requirements files - so the easiest way to install all just run:
- in case of CPU usage ``pip install -r requirements/cpu.txt``.
- in case of GPU usage ``pip install -r requirements/gpu.txt``.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].