BobLiu20 / Faciallandmark_caffe
Facial Landmark Detection with Caffe CNN. Face alignment avaiable.
Stars: ✭ 70
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Faciallandmark caffe
Wtdbg2
Redbean: A fuzzy Bruijn graph approach to long noisy reads assembly
Stars: ✭ 408 (+482.86%)
Mutual labels: alignment
Alignedcollectionviewflowlayout
A collection view layout that gives you control over the horizontal and vertical alignment of the cells.
Stars: ✭ 751 (+972.86%)
Mutual labels: alignment
Groot
A resistome profiler for Graphing Resistance Out Of meTagenomes
Stars: ✭ 48 (-31.43%)
Mutual labels: alignment
Mmseqs2
MMseqs2: ultra fast and sensitive search and clustering suite
Stars: ✭ 441 (+530%)
Mutual labels: alignment
Ffsubsync
Automagically synchronize subtitles with video.
Stars: ✭ 5,167 (+7281.43%)
Mutual labels: alignment
Facealignmentcompare
Empirical Study of Recent Face Alignment Methods
Stars: ✭ 15 (-78.57%)
Mutual labels: alignment
Align
A general purpose application and library for aligning text.
Stars: ✭ 63 (-10%)
Mutual labels: alignment
Aligntab
An alignment plugin for Sublime Text using regular expression
Stars: ✭ 611 (+772.86%)
Mutual labels: alignment
Unsupervisedrr
[CVPR 2021 - Oral] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering
Stars: ✭ 43 (-38.57%)
Mutual labels: alignment
Prnet
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)
Stars: ✭ 4,479 (+6298.57%)
Mutual labels: alignment
Pandas
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
Stars: ✭ 32,029 (+45655.71%)
Mutual labels: alignment
Alass
"Automatic Language-Agnostic Subtitle Synchronization"
Stars: ✭ 421 (+501.43%)
Mutual labels: alignment
Lambda
LAMBDA – the Local Aligner for Massive Biological DatA
Stars: ✭ 59 (-15.71%)
Mutual labels: alignment
Cmu Multimodalsdk
CMU MultimodalSDK is a machine learning platform for development of advanced multimodal models as well as easily accessing and processing multimodal datasets.
Stars: ✭ 388 (+454.29%)
Mutual labels: alignment
Edit Distance
Python library for computing edit distance between arbitrary Python sequences.
Stars: ✭ 61 (-12.86%)
Mutual labels: alignment
Alignmentduration
Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.
Stars: ✭ 36 (-48.57%)
Mutual labels: alignment
What's this
- Facial Landmark Detection with Caffe CNN.
- Implementation of the two nets from different paper.
- Net1: Approaching human level facial landmark localization by deep learning
- Net2: TCNN: Facial Landmark Detection with Tweaked Convolutional Neural Networks
How to prepare dataset
- Please download CelebA dataset
- change input path to your dataset path in train.prototxt file.
How to training
Please run these command in the root of this project. Note: Please change parameter in train.prototxt. such as process num and buffer2memory!
- set env
export PYTHONPATH=`pwd`/common/:$PYTHONPATH
- train net1
caffe train --solver=training/net1/solver.prototxt --gpu=0
- train net2
caffe train --solver=training/net2/vanilla_adam_solver.prototxt --gpu=0
How to testing or predict
cd testing
python test.py ../model/net1/_iter_100000.caffemodel ../training/net1/deploy.prototxt
Please replace correct path of caffe model and deploy file in above command.
How to do a benchmark
cd benchmark
python test.py ../model/net1/_iter_100000.caffemodel ../training/net1/deploy.prototxt
Please replace correct path of caffe model and deploy file in above command.
After do that, you will get mean error of your model.
Reference
Other DL framework
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].