The smallest dimension of a training or validation image is always 256 (e.g. Those images are ROI’s (regions of interest from other images) that I manually cropped in the past, so the whole (training) image consists of one specific object. I have 3 different object classes which I want to detect in images : classA, classB and classC.įor each object class, I have 3000 training images available (=> so 9000 in total), and 1500 validation images (=> 4500 in total). My case is a bit different from the comments that I found …
But apparently, most of the mentioned datasets consists of images with more or less the same dimensions for all images. I read some posts about adapting some settings in detectnet to use it for training and detection in a custom dataset. I want to use DIGITS (detectnet) + CAFFE to detect objects in my own dataset. I would love adding documentation to using DetectNet & Digits with a custom dataset, however I can't really understand everything yet. does not seem to need modification as it is the bounding box regressor so it should output 4 objects. However, I can't understand what I would need to modify: L2418. I would then guess param_str = 'xSize,ySize,Stride,?,?,?,?' but the rest.
Parallelforall spacenet full#
The issue is that in the blog post, the full modified prototxt is not published so I'm having a lot of trouble recalculating what I need to modify: I am also trying to adapt detectnet for my own dataset (example 1024x1024 size images) with custom object sizes (around 192x192)
0 kommentar(er)
