alterzero / dbpn-caffe Goto Github PK
View Code? Open in Web Editor NEWDeep Back-Projection Networks for Super-Resolution
License: MIT License
Deep Back-Projection Networks for Super-Resolution
License: MIT License
Could anyone give me some guidance on how to run the code in caffe environment?
I have tried several times. But it did not give me any results.
Thanks a lot!
Hi, thanks for your sharing.
Could you tell me that how can I train my own model?
Hi, thanks for sharing the code.
I am trying to test your pre trained model in pycaffe however I must be doing something wrong because the results is not as expected. Here is the code and the result.
scale = 4.0
test_img_path = "butterfly_GT.bmp"
net = caffe.Net("model/DBPN_mat_4x.prototxt", "model/DBPN_4x.caffemodel", caffe.TEST)
img = cv2.imread(test_img_path, cv2.IMREAD_COLOR)
img = modcrop(img, scale)
lr_img = cv2.resize(img, None, fx=1/scale, fy=1/scale, interpolation=cv2.INTER_CUBIC) / 255.0
lr_img = lr_img[np.newaxis, :, :, :]
b, w, h, c = lr_img.shape
lr_img = np.reshape(lr_img, [b, c, w, h])
net.blobs['data'].reshape(*lr_img.shape)
net.blobs['data'].data[...] = lr_img
out = net.forward()
pred_img = np.asarray(out['conv_final'])
pred_img = pred_img.squeeze()
pred_img = np.reshape(pred_img, [img.shape[0], img.shape[1], img.shape[2]])
I have installed matcaffe. And I have downloaded pretrained models.
But after I run DBPN_main_rgb.m at the root of DBPN-caffe which I have directly downloaded from GitHub. I only get the following results:
Bi cubic: NaN , NaN , NaN , NaN
dbpn: NaN , NaN , NaN , NaN
What's the matter with what l did? And could you tell me how I can get the correct results?
Thanks!!!
do you have training dataset for x8 case
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.