cai199626 / pdnet Goto Github PK
View Code? Open in Web Editor NEWfor RGBD salient object detection
for RGBD salient object detection
你好,我在别的地方看到你留言说在研究关于多机RGBD-SLAM的问题,因为我也在学习这个方面,所以想了解一下您的进展,方便沟通一下吗?
Can you privide data_ecssd_224x224x2_T.h5 for me?
I already down the vgg161_merge_224x224x2_weight.0.168.hdf5.
I want to jump preprocess.py and train.py.
I just want to test the result directly.
So can you privide data_ecssd_224x224x2_T.h5 or other preprocessing h5py file for me?
thank you for your attention
Hi, when i open the pre-trained model download link, it needs permission? can you share the pre-trained model in Baidu Yun?
您好,感谢您的代码。
想请问下,您的这个代码的训练流程是怎么样的?我看train.py应该是RGB图的训练,train_deep.py是RGB+Depth的训练?如果我想训练RGB-D的图的话,是不是直接训练train_deep.py就行呢?如果我想用自己的数据集的话,您提供的RGB-D的预训练权重是否可以很好的适应呢?
感谢
Hello, I'd like to use the network vgg16_deep_model,but i found in model.py ,the line 26,and 28,deep=images[:,:,:,3:4],but,images.shape=2242243, i check the preprocess.py,the image.shape still is 2242243,so ,if you use the depth cue,both the dataset has no depth image,so ,where did you get the depth cue,if you use ,can you chat with me
Hi, I have successfully preprocessed my data and when I run preprocess.py it generates data_merge_224x224x2_T.h5 but when trying to train I get:
Using TensorFlow backend.
channels_last
2019-01-10 14:49:54.773965: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
Then the process ends. I think that the cpu message can be ignored as I've had other models run successfully.
Either the model is not training or I'm doing something wrong when running test.py. You say to edit the test.py file but I'm not sure what needs editing here either. when I run test.py I get:
Using TensorFlow backend.
Traceback (most recent call last):
File "test.py", line 25, in
images = load()
File "test.py", line 15, in load
f = h5py.File('test_nlpr_224x224.h5','r')
File "/home/ds392/.local/lib/python3.6/site-packages/h5py/_hl/files.py", line 312, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/ds392/.local/lib/python3.6/site-packages/h5py/_hl/files.py", line 142, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = 'test_nlpr_224x224.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
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.