Description
From the previous versions of Darknet:
Download file with the first 29-convolutional layers of yolov4-tiny: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.conv.29 (Or get this file from yolov4-tiny.weights file by using command: darknet.exe
partialcfg/yolov4-tiny-custom.cfg yolov4-tiny.weights yolov4-tiny.conv.29 29
And:
darknet partial <CFG_FILE> <OLD_WEIGHTS_FILE> <NEW_WEIGHTS_FILE> <NUM_OF_LAYERS_TO_CUT>
The new V3 code that recognizes if loading the weights has failed due to either under-reading or attempting to over-read weights is currently triggering, as reported by a user on the discord tonight (#training-questions):
I'm attempting to use the "partial" command to cut the first n layers' weight values and utilize them when initiating a new training. However, when I try to load the cut weights, Darknet raises an error from the "xfread" method (expected to read 64 fields, but only read 0).