Tim Becker
Tim Becker
added check for valid bounding boxes. If an invalid bounding box is detected, an exception is thrown
When the training data contains invalid bounding boxes with ```box["x1"] > box["x2"]``` the loss drops to ```nan```. To solve this a simple check for box["x1"] < box["x2"] and box["y1"] <...
ClassifyPixels-Unet fails to process an image of size 695x520. The same image with a size of 696x520 works fine. Error message: ``` Error while processing ClassifyPixels-Unet: "concat" mode can only...
Some CellProfiler plugins need additional libraries. For example, to use the UNet plugin with the Windows version, the CNTK libraries need to be installed. For this, CellProfiler needs to be...
The module ClassifyPixels-Unet downloads and uses one UNet model that was trained on nuclei images. It would be great to have the option to load a custom model either from...
The module ClasssifyPixels-Unet uses keras with CNTK (windows) or tensorflow (Mac/Linux) backend with CPU support. It takes 10 seconds on a MacBook Pro and ~70seconds on a Windows laptop but...
The configuration file processes image data from the data set bbbc039 and the configuration file was renamed accordingly. It still contains the path ``` config_vars["root_directory"] = '/data1/image-segmentation/BBBC022/unet/' ``` I am...