alexanderparkin / chalearn_liveness_challenge Goto Github PK
View Code? Open in Web Editor NEWChaLearn Face Anti-spoofing Attack Detection Challenge@CVPR2019
License: MIT License
ChaLearn Face Anti-spoofing Attack Detection Challenge@CVPR2019
License: MIT License
hi,everbody. I run inference.sh ,but have a error is it can not found model_30.pth in the follow path:"
data/opts/exp1_2stage_seed1/fold${i}/checkpoints/model_30.pth。In this path,I cannot found the model file.where i should be download?
How to use this project to process actual production photos or videos,Thank you very much for any help you can give.
我如何将这个项目用于实际生产项目,能否给予demo来识别一张照片?
During the installation of the requirements:
(python3) (ChaLearn) marco@pc:~/antiFaceSpoofing/ChaLearn_liveness_challenge-master$
pip3 install -r requirements.txt
Running setup.py install for pandocfilters ... done
Running setup.py install for line-profiler ... error
Complete output from command /home/marco/antiFaceSpoofing
/ChaLearn_liveness_challenge-master/ChaLearn/bin/python3 -u -c "import setuptools,
tokenize;__file__='/tmp/pip-install-3l1jfhn8/line-profiler/setup.py';f=getattr(tokenize, 'open',
open)(__file__);code=f.read().replace('\r\n', '\n');f.close();exec(compile(code, __file__, 'exec'))"
install --record /tmp/pip-record-4guy7wor/install-record.txt --single-version-externally-managed
--compile --install-headers /home/marco/antiFaceSpoofing/ChaLearn_liveness_challenge-
master/ChaLearn/include/site/python3.7/line-profiler:
Could not import Cython. Using the available pre-generated C file.
running install
running build
running build_py
creating build
creating build/lib.linux-x86_64-3.7
copying line_profiler.py -> build/lib.linux-x86_64-3.7
copying kernprof.py -> build/lib.linux-x86_64-3.7
copying line_profiler_py35.py -> build/lib.linux-x86_64-3.7
running build_ext
building '_line_profiler' extension
creating build/temp.linux-x86_64-3.7
gcc -pthread -B /home/marco/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare
-DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/marco/antiFaceSpoofing
/ChaLearn_liveness_challenge-master/ChaLearn/include -I/home/marco/anaconda3/include
/python3.7m -c _line_profiler.c -o build/temp.linux-x86_64-3.7/_line_profiler.o
In file included from _line_profiler.c:476:0:
unset_trace.h:1:1: warning: function declaration isn’t a prototype [-Wstrict-prototypes]
void unset_trace();
^~~~
_line_profiler.c: In function ‘__Pyx__ExceptionSave’:
_line_profiler.c:7890:21: error: ‘PyThreadState {aka struct _ts}’ has no member named
‘exc_type’; did you mean ‘curexc_type’?
*type = tstate->exc_type;
^~~~~~~~
curexc_type
_line_profiler.c:7891:22: error: ‘PyThreadState {aka struct _ts}’ has no member named
‘exc_value’; did you mean ‘curexc_value’?
*value = tstate->exc_value;
^~~~~~~~~
curexc_value
_line_profiler.c:7892:19: error: ‘PyThreadState {aka struct _ts}’ has no member named
‘exc_traceback’; did you mean ‘curexc_traceback’?
*tb = tstate->exc_traceback;
^~~~~~~~~~~~~
curexc_traceback
_line_profiler.c: In function ‘__Pyx__ExceptionReset’:
_line_profiler.c:7899:24: error: ‘PyThreadState {aka struct _ts}’ has no member named
‘exc_type’; did you mean ‘curexc_type’?
tmp_type = tstate->exc_type;
^~~~~~~~
curexc_type
I see that you have resized your pictures. What are the specifications of your pictures after resize?
In Ubuntu 18.04.02 Server Edition,
I downloaded all the pre-trained models in data folder:
(python3) marco@pc:~/ChaLearn_liveness_challenge/data$ ls -lah
total 559M
drwxrwxr-x 4 marco marco 4.0K Oct 9 12:03 .
drwxrwxr-x 10 marco marco 4.0K Oct 9 11:54 ..
-rw-r--r-- 1 marco marco 167M Mar 14 2019 backbone_ir50_asia.pth
-rw-r--r-- 1 marco marco 167M Mar 14 2019 backbone_ir50_ms1m_epoch120.pth
drwxrwxr-x 3 marco marco 4.0K Oct 9 11:01 lists
drwxrwxr-x 9 marco marco 4.0K Oct 9 10:06 opts
-rw-rw-r-- 1 marco marco 5.3M Oct 9 11:04 predict_sample.txt
-rw-r--r-- 1 marco marco 111M Mar 14 2019 resnet_caffe_afad_lite_g_exp1.pth
-rw-r--r-- 1 marco marco 111M Mar 14 2019 resnet_caffe_mcs_orgl.pth
But when executing train.sh :
(python3) marco@pc:~/ChaLearn_liveness_challenge$ ./train.sh
Traceback (most recent call last):
File "main.py", line 7, in <module>
from trainer import Model
File "/home/marco/ChaLearn_liveness_challenge/trainer.py", line 9, in <module>
import models, datasets, utils
File "/home/marco/ChaLearn_liveness_challenge/models/__init__.py", line 1, in <module>
from .init_model import init_loss, get_model
File "/home/marco/ChaLearn_liveness_challenge/models/init_model.py", line 1, in
<module>
from .architectures import MobileNetV2
File "/home/marco/ChaLearn_liveness_challenge/models/architectures/__init__.py", line 1,
in <module>
from .mobilenetv2b import MobileNetV2
ModuleNotFoundError: No module named 'models.architectures.mobilenetv2b'
How to solve the problem?
Marco
Traceback (most recent call last):
File "inference.py", line 7, in
from trainer import Model
File "/home/qing/face/visionlabs/trainer.py", line 9, in
import models, datasets, utils
File "/home/qing/face/visionlabs/models/init.py", line 1, in
from .init_model import init_loss, get_model
File "/home/qing/face/visionlabs/models/init_model.py", line 1, in
from .architectures import MobileNetV2
File "/home/qing/face/visionlabs/models/architectures/init.py", line 1, in
from .mobilenetv2b import MobileNetV2
ModuleNotFoundError: No module named 'models.architectures.mobilenetv2b'
Hello, I look at your inference code carefully, it need to input pictures of three modes. I only use infrared pictures to test, will it affect the accuracy of the test?Because I only have infrared pictures. @AlexanderParkin
根本看不懂怎么运行,模型我已经下载好了
@AlexanderParkin It looks like the model link isn't working, could you please update? Thanks!
we see that there is a SE block on CVPR2019 at Figure 2, but not seen at the figure of this repo as well as 'resnetDLAS_A' on resnet_caffe_DLAS.py. I wonder if the performance shown at paper Table 3 of line:
"A. resnet-34 with MLFA | CASIA-Web face [25] | attack 3-fold | 99.87" including SE block, or, in other words, which architecture from the code is 'resnet-34 with MLFA ', is that 'resnetDLAS_A' ?
@AlexanderParkin All links are invalid. Can you update the model files? Thank you so much.
Hi!
Regarding the spec-file.txt file, I'm not sure if it is possible to run this project in Windows.
In the file used to create the conda environment, it is explained that the platform to be used is linux-64.
I tried to create the conda environment using this original file, and also to create it by modifying it to download windows libraries., but it does not work for me.
Any idea on how to correctly create the conda environment in windows? do you have another spec-file.txt?
Thanks in advance!
Hello,
I can't download the pretrained model for exp1_2stage, the link is broken. Where can I find it?
I think the author has not double check the repo. Many error and missing file in this repo. If someone has sucess run it, please let me know
Hello, can you post a link to the paper, thank you~
hello, how about time-consuming? and how many params?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.