songdejia / Dfl Cnn
Licence: mit
This is a pytorch re-implementation of Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition
Stars: ✭ 245
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Dfl Cnn
Liteflownet
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
Stars: ✭ 474 (+93.47%)
Mutual labels: cnn, cvpr2018
Audio-Classification-using-CNN-MLP
Multi class audio classification using Deep Learning (MLP, CNN): The objective of this project is to build a multi class classifier to identify sound of a bee, cricket or noise.
Stars: ✭ 36 (-85.31%)
Mutual labels: classifier, cnn
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-51.02%)
Mutual labels: cnn, classifier
Dcpdn
Densely Connected Pyramid Dehazing Network (CVPR'2018)
Stars: ✭ 321 (+31.02%)
Mutual labels: cnn, cvpr2018
Did Mdn
Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)
Stars: ✭ 192 (-21.63%)
Mutual labels: cnn, cvpr2018
Person Attribute Recognition Marketduke
A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.
Stars: ✭ 224 (-8.57%)
Mutual labels: cnn
Convolution network on fpga
CNN acceleration on virtex-7 FPGA with verilog HDL
Stars: ✭ 236 (-3.67%)
Mutual labels: cnn
Deform conv pytorch
PyTorch Implementation of Deformable Convolution
Stars: ✭ 217 (-11.43%)
Mutual labels: cnn
Tcdf
Temporal Causal Discovery Framework (PyTorch): discovering causal relationships between time series
Stars: ✭ 217 (-11.43%)
Mutual labels: cnn
Caption generator
A modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.
Stars: ✭ 243 (-0.82%)
Mutual labels: cnn
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+1209.8%)
Mutual labels: cnn
Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+977.96%)
Mutual labels: cnn
Cnn Text Classification Tf Chinese
CNN for Chinese Text Classification in Tensorflow
Stars: ✭ 237 (-3.27%)
Mutual labels: cnn
Natural Language Processing With Tensorflow
Natural Language Processing with TensorFlow, published by Packt
Stars: ✭ 222 (-9.39%)
Mutual labels: cnn
Gordon cnn
A small convolution neural network deep learning framework implemented in c++.
Stars: ✭ 241 (-1.63%)
Mutual labels: cnn
Smoothly Blend Image Patches
Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.
Stars: ✭ 218 (-11.02%)
Mutual labels: cnn
Pytorch Multi Label Classifier
A pytorch implemented classifier for Multiple-Label classification
Stars: ✭ 232 (-5.31%)
Mutual labels: classifier
Hierarchical Attention Networks Pytorch
Hierarchical Attention Networks for document classification
Stars: ✭ 239 (-2.45%)
Mutual labels: cnn
Ai Toolbox
Algorithm Engineer Toolbox, for the purpose of quickly iterating new ideas
Stars: ✭ 230 (-6.12%)
Mutual labels: cnn
DFL-CNN : a fine-grained classifier
This is a simple pytorch re-implementation of CVPR 2018 Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition.
Introduction:
This work still need to be updated. The features are summarized blow:
- Use VGG16 as base Network.
- Dataset CUB-200-2011, you can split trainset/testset by yourself.Or you can download dataset which has been split directly from BaiduYun Link.
- This work has been trained on 4 Titan V after epoch 120 with batchsize 56, Now I got best result Top1 85.140% Top5 96.237% which is lower than author's. You can download weights from weights.
- Part FCs is replaced by Global Average Pooling to reduce parameters.
- Every some epoches, ten best patches is visualized in vis_result directory, you can put images you want to visualize in vis_img named number.jpg.
- Update: ResNet-101 DFL-CNN and Multi-scale DFL-CNN need to be done.
Algorithms Introduction:
Results and Visualization of ten boxes for discriminative patches:
-
This work has been trained on 4 Titan V after epoch 120 with batchsize 56, Now I got best result Top1 85.140% Top5 96.237% which is lower than author's. You can download weights from weights. If use TenCrop transform in code, result can improve further.
-
Test Results:
- Visualization:
Usage:
- Download dataset, you can split trainset/valset by yourself
wget http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz
- Or you can directly get it from BaiduYun Link
- Then link original dataset to our code root/dataset
ln -s ./train path/to/code/dataset/train
ln -s ./test path/to/code/dataset/test
- Finally, Train and Test.
- Check you GPU resources and modify your run.sh.
sh run.sh
Note:
- Visualization of ten best boxes is saved in vis_result/, img you want to visualize should be put in vis_img/.
- Weight(checkpoint.pth.tar, model_best.pth.tar) is in weight/.
- Loss info is saved in log/.
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].