Randl / Shufflenetv2 Pytorch
Licence: mit
Implementation of ShuffleNetV2 for pytorch
Stars: ✭ 148
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Shufflenetv2 Pytorch
Music-Genre-Classification
Genre Classification using Convolutional Neural Networks
Stars: ✭ 27 (-81.76%)
Mutual labels: cnn-model
Deeptraffic
Deep Learning models for network traffic classification
Stars: ✭ 321 (+116.89%)
Mutual labels: cnn-model
Cnn Text Classification Pytorch
CNNs for Sentence Classification in PyTorch
Stars: ✭ 845 (+470.95%)
Mutual labels: cnn-model
CompareModels TRECQA
Compare six baseline deep learning models on TrecQA
Stars: ✭ 61 (-58.78%)
Mutual labels: cnn-model
Evil
Optical Character Recognition in Swift for iOS&macOS. 银行卡、身份证、门牌号光学识别
Stars: ✭ 648 (+337.84%)
Mutual labels: cnn-model
SpeakerDiarization RNN CNN LSTM
Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).
Stars: ✭ 56 (-62.16%)
Mutual labels: cnn-model
Deep sort pytorch
MOT using deepsort and yolov3 with pytorch
Stars: ✭ 1,948 (+1216.22%)
Mutual labels: cnn-model
Resnetcam Keras
Keras implementation of a ResNet-CAM model
Stars: ✭ 269 (+81.76%)
Mutual labels: cnn-model
Facerank
FaceRank - Rank Face by CNN Model based on TensorFlow (add keras version). FaceRank-人脸打分基于 TensorFlow (新增 Keras 版本) 的 CNN 模型（QQ群：167122861）。技术支持：http://tensorflow123.com
Stars: ✭ 841 (+468.24%)
Mutual labels: cnn-model
yolo-deepsort-flask
Target detection and multi target tracking platform based on Yolo DeepSort and Flask.
Stars: ✭ 29 (-80.41%)
Mutual labels: cnn-model
Speech Emotion Recognition
Using Convolutional Neural Networks in speech emotion recognition on the RAVDESS Audio Dataset.
Stars: ✭ 63 (-57.43%)
Mutual labels: cnn-model
Captcha Tensorflow
Image Captcha Solving Using TensorFlow and CNN Model. Accuracy 90%+
Stars: ✭ 660 (+345.95%)
Mutual labels: cnn-model
VoiceNET.Library
.NET library to easily create Voice Command Control feature.
Stars: ✭ 14 (-90.54%)
Mutual labels: cnn-model
Cnn Models
ImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (+139.86%)
Mutual labels: cnn-model
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-18.92%)
Mutual labels: cnn-model
Cnn Yelp Challenge 2016 Sentiment Classification
IPython Notebook for training a word-level Convolutional Neural Network model for sentiment classification task on Yelp-Challenge-2016 review dataset.
Stars: ✭ 106 (-28.38%)
Mutual labels: cnn-model
Cnn Lstm Bilstm Deepcnn Clstm In Pytorch
In PyTorch Learing Neural Networks Likes CNN(Convolutional Neural Networks for Sentence Classification (Y.Kim, EMNLP 2014) 、LSTM、BiLSTM、DeepCNN 、CLSTM、CNN and LSTM
Stars: ✭ 714 (+382.43%)
Mutual labels: cnn-model
ShuffleNetv2 in PyTorch
An implementation of ShuffleNetv2 in PyTorch. ShuffleNetv2 is an efficient convolutional neural network architecture for mobile devices. For more information check the paper:
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Usage
Clone the repo:
git clone https://github.com/Randl/ShuffleNetV2-pytorch
pip install -r requirements.txt
Use the model defined in model.py to run ImageNet example:
python imagenet.py --dataroot "/path/to/imagenet/"
To continue training from checkpoint
python imagenet.py --dataroot "/path/to/imagenet/" --resume "/path/to/checkpoint/folder"
Results
For x0.5 model I achieved 0.4% lower top-1 accuracy than claimed.
| Classification Checkpoint | MACs (M) | Parameters (M) | Top-1 Accuracy | Top-5 Accuracy | Claimed top-1 | Claimed top-5 |
|---|---|---|---|---|---|---|
| [shufflenet_v2_0.5] | 41 | 1.37 | 59.86 | 81.63 | 60.3 | - |
You can test it with
python imagenet.py --dataroot "/path/to/imagenet/" --resume "results/shufflenet_v2_0.5/model_best.pth.tar" -e --scaling 0.5
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].