simrdwn icon indicating copy to clipboard operation
simrdwn copied to clipboard

Rapid satellite imagery object detection

Results 27 simrdwn issues
Sort by recently updated
recently updated
newest added

Do you have a Pytorch version, thank you.

Hi, I tried to mount the docker image from branch master, both on local system and and Google Cloud Platform. In both cases I run out of memory at step...

Are there any pretrained weights available somewhere? If not, that might be of value, and of greater value if you add those to the docker image, so people can use...

I've attached the inference results using the simrdwn. As you can see, the detection is quite good, but I'm not sure why (for most of the buildings at least) the...

When I was training the network, I met a problem that the loss was all 0. I couldn't solve it. The framework I used was yolt3.This is my command ![)PVTQOAA%`WQY@`(987FURF](https://user-images.githubusercontent.com/56947252/70370500-de64d300-1902-11ea-8db9-b0596a5f96e6.png)...

I was trying to reproduce the result with COWC, however, there are no cars detected during test time while the loss curve during training time looks reasonable: ![yolt_loss_plot_tiny_cowc](https://user-images.githubusercontent.com/10052602/57990905-e8ef7600-7a5f-11e9-97ed-d12775f08ee1.png) I was...

I'm receiving the following error after following the readme steps: ``` (simrdwn) root@0c3ed625799b:/# python /simrdwn/simrdwn/core/simrdwn.py --help Traceback (most recent call last): File "/opt/conda/envs/simrdwn/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow.py", line 58, in from tensorflow.python.pywrap_tensorflow_internal import *...

@avanetten I would like to train different sizes of sliced images. Not only 416, or 544. It maybe mixed with 416 and 544, or other. How can I do it?...

Dear Adam, Thank you for your great works!! I downloaded the simrdwn/data a week and half ago and worked on it. Again I just downloaded another version of source code...

I cannot get simrdwn to train. It is telling me (via tensorflow) that my CUDA driver version is insufficient for CUDA runtime version. I know this seems like it is...