IMELE
IMELE copied to clipboard
speed8928
Hello, thanks for your nice work. The code ("depth = (depth*1000).astype(np.uint16)") is applied in the loaddata.py. As far as I know, the upper bound of uint16 is 65535, but some...
By downloading the OSI data you provided, I found that DSM data is in uint16 format, so do you still need the following processing in dataloader? ` depth = cv2.imread(depth_name,-1);...
Hi ! I tried integrating your model into my own pipeline, and seem to have run into some issues. I tried porting your loss implementation into proper modules, but for...
Good afternoon! Thanks for sharing such exciting work. I've been trying to load in your trained weights to a `model` defined by the following (`is_senet=True`): ```python original_model = senet154(pretrained='imagenet') Encoder...
- add Docker: to easily create an environment, reproductivity - requirements.txt: determined versions - .dockerignore: exclude files when building Docker - change `async`: in the latest python, `async` is a...
Hello, thanks for your good work. There are some questions about the training data (Vaihingen dataset and Potsdam dataset). Is the ground-truth in your training DSM or normalized DSM? Could...
Thanks for your work. Did you perform post-processing to merge the predicted height image patches and generate the seamless height map?
Test.py
Hello, after my debugging, I can run the training and test. I want to ask what will happen if I run the test folder. I only output the data of...
I was executing the code and faced this error can you please guide me on this because most of the solutions on different sites haven't worked for me. I am...
Thanks for sharing this work @speed8928. However, I couldn't use the provided pre-trained model and get meaningful prediction for another area. The issues are: 1. Output is not representative of...
