FCRN-DepthPrediction
FCRN-DepthPrediction copied to clipboard
irolaina
Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)
Will you show your code for training in Tensorflow version? It is hard to train on the dataset. Thank U!
I cannot find the code that is used to train your model, will you be making it available soon please? I would like to experiment with different data sets. :)
Hello, it is a great work. But I just test your predicted map provided by yourself and cannot get same error like your paper, I test it with matlab. your...
After using the predict.py codes provided, I was able to obtain test images, however, there were black boxes on each side of the images as shown below. I was wondering...
Hi, I check the NYU_FCRN.ckpt model you provide for us. The NYU_FCRN.ckpt.data-00000-of-00001 save parameters is 245.5MB. However, I train FCRN and save the model, it took 508.5MB. I don't know...
I am working on a project that require real time RGB-D data and i was thinking about using this work to generate the depth map of a live stream to...
Hello, I am trying to build my own network in TF, based on your results. I know for sure that I built the correct model because I am able to...
Could you tell me which optimizer did you use, and about learning rate ? Also how can I evalute the model？
The depth map predicted by both matconvnet and tensorflow weights are coming very blur. Please help.
Hi, @iro-cp I have test your result on nyu_label dataset (use test 654 images, tf-model is provided by you) , http://horatio.cs.nyu.edu/mit/silberman/nyu_depth_v2/nyu_depth_v2_labeled.mat  There is my error calculate method, (a1 corresponding...
