alterzero / dbpn-caffe Goto Github PK

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