Lloyd Hughes
Lloyd Hughes
I have an application whereby I am manually forming a dask array using `blocks` as each of the chunks in the final array need to go through a specific transform...
Hi, Firstly this project is great, really excellent work! I have a problem I am trying to solve, and currently have a solution using POVRay, however, the solution is slow...
sarsen (https://github.com/bopen/sarsen) is a fairly recent initiative to re-implement Sentinel-1 preprocessing and calibration using modern Python libraries such as Dask and XArray. This enables better scalability over distributed clusters of...
I have an application where I need to label time-series imagery, I cannot simply convert the images to single images and label those as I am trying to track differences...
I generated the docs as I saw something on transfer learning, however, the docs don't seem complete. Is there a way to load the ReNet18 with weights based on ImageNet...
I am seeing a problem where if I call `get_collections` directly it is very slow and only the first page of the collections are returned. If I reimplement the `get_collections`...
An additional dataset which is specifically made for deep learning on SAR and optical imagery is the SEN1-2 dataset. Contains around 250K corresponding patch pairs of Sentinel 1 (VV) and...
**Describe the bug** I have two OLCI L2 WFR products `S3B_OL_2_WFR____20230327T075434_20230327T075734_20230328T175956_0179_077_320_3600_MAR_O_NT_003.SEN3` `S3B_OL_2_WFR____20230327T075134_20230327T075434_20230328T175940_0179_077_320_3420_MAR_O_NT_003.SEN3` In my old pipeline I used SNAP GPT to mosaic these products together (there is limited overlapping between...
Will you be sharing the downstream task datasets so other SSL approaches can benchmark in comparison to yours?
OSX Compilation was not supported out of the box so I just added the correct paths and a small section to find the paths based on the OS and architecture...