-
Hello,
Is there a simple example on how to setup a One to Many RNN case for uses in say an Image Captioning application? How should one go about doing it using your CNTK API?
Thanks!
-
-
Consider a priori:
- baseline: pyramidal strategy
- FB 360 upcoming strategy: replace the deep neural network with [1] below
Ouput:
- document of specification of the pyramidal strategy (with de…
-
i ran the following script ,
`sudo python align_dataset_mtcnn.py /datasets/lfw/raw /datasets/lfw/lfw_mtcnnpy_160 --image_size 160 --margin 32 --random_order --gpu_memory_fraction 0.25 `
May I kn…
-
Are there any CNTK tutorials that deal with video inputs or any plans to add some?
-
I want to use my own data to make a fine-tuning training. I found the ground truth of HED-BSDS, the edge image contains different gray values. I wonder all the edge with different gray value will be u…
-
Congrats for best paper on CVPR 2017!
I'm troubled with the memory problem with densenet. Would you share your wide-densenet implementation and pre-train models publicly?
Best!
-
Hi,
As I go through the code, the evaluation on test sets (new image) is perfect, however, I can not find the evaluation corresponding to the new object, which is referred as 'uniformly sampling ob…
-
I have been using openMVS for modeling with openMVG.
openMVS works great till 60-70 images, but it crashes at Densepoint as soon as the number of images crosses 70.
Is there a more scalable solutio…
-