potterhsu / Svhnclassifier Pytorch
Licence: mit
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)
Stars: ✭ 141
Projects that are alternatives of or similar to Svhnclassifier Pytorch
Geometric Intuition
Understanding ML and deep learning through geometry
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Textrank text summarization
A tutorial for Automatic Text Summarization using TextRank algorithm.
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Notebook
Collection of jupyter notebooks for demonstrating software.
Stars: ✭ 141 (+0%)
Mutual labels: jupyter-notebook
Kdd winniethebest
KDD Cup 2020 Challenges for Modern E-Commerce Platform: Multimodalities Recall first place
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Cutout Random Erasing
Cutout / Random Erasing implementation, especially for ImageDataGenerator in Keras
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Byte Sized Code
A collection of Jupyter notebooks for learning Python from the ground up.
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Lessonmaterials
Open Sourced Curriculum and Lessons for an Introductory AI/ML Course
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Jupytext.vim
Vim plugin for editing Jupyter ipynb files via jupytext
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Dse210 probability statistics python
Probability and Statistics Using Python Data Science Masters Course at UCSD (DSE 210)
Stars: ✭ 141 (+0%)
Mutual labels: jupyter-notebook
Natural Language Processing Tutorials
Natural Language Processing Tutorials(NLP) with Julia and Python
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Makeyourownneuralnetwork
Code for the Make Your Own Neural Network book
Stars: ✭ 1,859 (+1218.44%)
Mutual labels: jupyter-notebook
Lacmus
Lacmus is a cross-platform application that helps to find people who are lost in the forest using computer vision and neural networks.
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
Mlnd distracted driver detection
基于深度学习的驾驶员状态检测,不仅仅可以识别出疲劳驾驶,还能够识别出各种各样的状态
Stars: ✭ 141 (+0%)
Mutual labels: jupyter-notebook
Torchtext Summary
torchtext使用总结,从零开始逐步实现了torchtext文本预处理过程,包括截断补长,词表构建,使用预训练词向量,构建可用于PyTorch的可迭代数据等步骤。并结合Pytorch实现LSTM.
Stars: ✭ 142 (+0.71%)
Mutual labels: jupyter-notebook
SVHNClassifier-PyTorch
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
If you're interested in C++ inference, move HERE
Results
Steps | GPU | Batch Size | Learning Rate | Patience | Decay Step | Decay Rate | Training Speed (FPS) | Accuracy |
---|---|---|---|---|---|---|---|---|
54000 | GTX 1080 Ti | 512 | 0.16 | 100 | 625 | 0.9 | ~1700 | 95.65% |
Sample
$ python infer.py -c=./logs/model-54000.pth ./images/test-75.png
length: 2
digits: 7 5 10 10 10
$ python infer.py -c=./logs/model-54000.pth ./images/test-190.png
length: 3
digits: 1 9 0 10 10
Loss
Requirements
-
Python 3.6
-
torch 1.0
-
torchvision 0.2.1
-
visdom
$ pip install visdom
-
h5py
In Ubuntu: $ sudo apt-get install libhdf5-dev $ sudo pip install h5py
-
protobuf
$ pip install protobuf
-
lmdb
$ pip install lmdb
Setup
-
Clone the source code
$ git clone https://github.com/potterhsu/SVHNClassifier-PyTorch $ cd SVHNClassifier-PyTorch
-
Download SVHN Dataset format 1
-
Extract to data folder, now your folder structure should be like below:
SVHNClassifier - data - extra - 1.png - 2.png - ... - digitStruct.mat - test - 1.png - 2.png - ... - digitStruct.mat - train - 1.png - 2.png - ... - digitStruct.mat
Usage
-
(Optional) Take a glance at original images with bounding boxes
Open `draw_bbox.ipynb` in Jupyter
-
Convert to LMDB format
$ python convert_to_lmdb.py --data_dir ./data
-
(Optional) Test for reading LMDBs
Open `read_lmdb_sample.ipynb` in Jupyter
-
Train
$ python train.py --data_dir ./data --logdir ./logs
-
Retrain if you need
$ python train.py --data_dir ./data --logdir ./logs_retrain --restore_checkpoint ./logs/model-100.pth
-
Evaluate
$ python eval.py --data_dir ./data ./logs/model-100.pth
-
Visualize
$ python -m visdom.server $ python visualize.py --logdir ./logs
-
Infer
$ python infer.py --checkpoint=./logs/model-100.pth ./images/test1.png
-
Clean
$ rm -rf ./logs or $ rm -rf ./logs_retrain
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].