sepidehhosseinzadeh / Fast Shadow Detection
Fast Shadow Detection from a Single Image Using a Patched CNN
Stars: ✭ 24
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Fast Shadow Detection
Ai sudoku
GUI based Smart Sudoku Solver that tries to extract a sudoku puzzle from a photo and solve it
Stars: ✭ 830 (+3358.33%)
Mutual labels: cnn
Mpcnn
Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Network复现
Stars: ✭ 22 (-8.33%)
Mutual labels: cnn
Tensorflow Tutorial
TensorFlow and Deep Learning Tutorials
Stars: ✭ 748 (+3016.67%)
Mutual labels: cnn
Codes For Lane Detection
Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)
Stars: ✭ 801 (+3237.5%)
Mutual labels: cnn
Dlib face recognition from camera
Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别
Stars: ✭ 719 (+2895.83%)
Mutual labels: cnn
Squeezenet v1.2
Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1.
Stars: ✭ 23 (-4.17%)
Mutual labels: cnn
Quickdraw
Implementation of Quickdraw - an online game developed by Google
Stars: ✭ 805 (+3254.17%)
Mutual labels: cnn
Srgan Tensorflow
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
Stars: ✭ 754 (+3041.67%)
Mutual labels: cnn
Tensorflow Tutorial
Some interesting TensorFlow tutorials for beginners.
Stars: ✭ 893 (+3620.83%)
Mutual labels: cnn
Self driving pi car
A deep neural network based self-driving car, that combines Lego Mindstorms NXT with the computational power of a Raspberry Pi 3.
Stars: ✭ 744 (+3000%)
Mutual labels: cnn
Exemplar Cnn
Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
Stars: ✭ 16 (-33.33%)
Mutual labels: cnn
Deepfakes video classification
Deepfakes Video classification via CNN, LSTM, C3D and triplets
Stars: ✭ 24 (+0%)
Mutual labels: cnn
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-4.17%)
Mutual labels: cnn
Eda nlp
Data augmentation for NLP, presented at EMNLP 2019
Stars: ✭ 902 (+3658.33%)
Mutual labels: cnn
Fast Shadow Detection from a Single Image Using a Patched CNN
This code is for the paper: S Hosseinzadeh, etc. "Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network", Proceedings of the IEEE/IROS 2018, https://arxiv.org/abs/1709.09283
Generating The Shadow Prior Map Images
- These images are used as image-level prior that are defined in line 44 of main_fast_shadow_detection.py.
- Install Paired_Region_Prob_Map using README in the folder. Run Paired_Region_Prob_Map/deshadow_driver.m by MATLAB
- Reference paper http://dhoiem.cs.illinois.edu/publications/pami12_shadow.pdf
Dependencies:
- nolearn
- lasagne
- theano
- scipy
- sklearn
- matplotlib
- skimage
- Python’s basic libraries (pickle, sys, os, urllib, gzip, cPickle, h5py, math, time, pdb)
How To Run The Code:
- python2.7: run main_fast_shadow_detection.py
- python3: run main_fast_shadow_detection_p3.py
Notes:
- Build folders "data_cache" and "prediction_output_v1" for data training/testing output files, and output prediction result files.
- TrainImgeFolder: Training Images
- TrainMaskFolder: Training Masks (Ground Truth)
- TrainFCNFolder: Shadow Prior Map Images
- Likewise for testing images…
- The Mask and Shadow Prior files should have 1 dimension, and Mask files also should be binary.
Using GPU:
Build a file in your home ~/.theanorc with a content of:
[global]
floatX = float32
[nvcc]
fastmath = True
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].