tomrunia / Pytorchconv3d
Licence: apache-2.0
I3D and 3D-ResNets in PyTorch
Stars: ✭ 131
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pytorchconv3d
Resnet Imagenet Caffe
train resnet on imagenet from scratch with caffe
Stars: ✭ 105 (-19.85%)
Mutual labels: resnet
Ir Net
This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.
Stars: ✭ 119 (-9.16%)
Mutual labels: resnet
Imagenet
This implements training of popular model architectures, such as AlexNet, ResNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet)
Stars: ✭ 126 (-3.82%)
Mutual labels: resnet
Resnet Face Pytorch
Training a ResNet on UMDFaces for face recognition
Stars: ✭ 107 (-18.32%)
Mutual labels: resnet
Shiftresnet Cifar
ResNet with Shift, Depthwise, or Convolutional Operations for CIFAR-100, CIFAR-10 on PyTorch
Stars: ✭ 112 (-14.5%)
Mutual labels: resnet
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+966.41%)
Mutual labels: resnet
Pytorch Speech Commands
Speech commands recognition with PyTorch
Stars: ✭ 128 (-2.29%)
Mutual labels: resnet
3d Tiles Samples
Sample tilesets for learning how to use 3D Tiles 📚
Stars: ✭ 115 (-12.21%)
Mutual labels: 3d-models
Arkit Unity3d
Access ARKit features like world-tracking, live video rendering, plane estimation and updates, hit-testing API, ambient light estimation, and raw point cloud data.
Stars: ✭ 124 (-5.34%)
Mutual labels: 3d-models
Duckyspark
Translator from USB-Rubber-Ducky payloads to a Digispark code.
Stars: ✭ 107 (-18.32%)
Mutual labels: 3d-models
Shot Type Classifier
Detecting cinema shot types using a ResNet-50
Stars: ✭ 109 (-16.79%)
Mutual labels: resnet
Resnet On Cifar10
Reimplementation ResNet on cifar10 with caffe
Stars: ✭ 123 (-6.11%)
Mutual labels: resnet
Awsome deep geometry learning
A list of resources about deep learning solutions on 3D shape processing
Stars: ✭ 105 (-19.85%)
Mutual labels: 3d-models
R Dfpn fpn tensorflow
R-DFPN: Rotation Dense Feature Pyramid Networks (Tensorflow)
Stars: ✭ 126 (-3.82%)
Mutual labels: resnet
Pyramidnet
Torch implementation of the paper "Deep Pyramidal Residual Networks" (https://arxiv.org/abs/1610.02915).
Stars: ✭ 121 (-7.63%)
Mutual labels: resnet
Pytorch Imagenet Cifar Coco Voc Training
Training examples and results for ImageNet(ILSVRC2012)/CIFAR100/COCO2017/VOC2007+VOC2012 datasets.Image Classification/Object Detection.Include ResNet/EfficientNet/VovNet/DarkNet/RegNet/RetinaNet/FCOS/CenterNet/YOLOv3.
Stars: ✭ 130 (-0.76%)
Mutual labels: resnet
Nips16 ptn
Torch Implementation of NIPS'16 paper: Perspective Transformer Nets
Stars: ✭ 126 (-3.82%)
Mutual labels: 3d-models
3D ConvNets in PyTorch
This repository contains PyTorch models of I3D and 3D-ResNets based on the following repositories:
- https://github.com/piergiaj/pytorch-i3d/blob/master/pytorch_i3d.py
- https://github.com/kenshohara/3D-ResNets-PyTorch/
Models: I3D, 3D-ResNet, 3D-DenseNet, 3D-ResNeXt
Datasets: UCF-101, Kinetics, ActivityNet, Charades
Installation
Clone and install:
git clone https://github.com/tomrunia/PyTorchConv3D.git
cd PyTorchConv3D
pip install -r requirements.txt
python setup.py install
Requirements
- Python 2.7 or 3.5+ (developed with 3.7)
- Numpy (developed with 1.15.0)
- PyTorch >= 0.4.0
- TensorboardX (optional)
- PIL (optional)
Examples
Training ResNet-34 from scratch on UCF-101
python train.py --dataset=ucf101 --model=resnet --video_path=/home/tomrunia/data/UCF-101/jpg --annotation_path=/home/tomrunia/data/UCF-101/ucfTrainTestlist/ucf101_01.json --batch_size=64 --num_classes=101 --momentum=0.9 --weight_decay=1e-3 --model_depth=34 --resnet_shortcut=A --spatial_size=112 --sample_duration=16 --optimizer=SGD --learning_rate=0.01
References
- Carreira and Zisserman - "Quo Vadis, Action Recognition?" (CVPR, 2017)
- Hara et al. - "Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?" (CVPR, 2018)
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].