lccui
lccui
The images in the test_results can not open
bmp has bogus header data.how to fix it?
> I have the same problem of Iccui. Did you find a solution to that? “Try using some other image viewer. I could not open using default Image Viewer in...
yolov4: mish to leaky is ok. I0825 16:46:47.052114 9499 net.cpp:257] Network initialization done. unknow layer type yolo unknow layer type yolo save prototxt to prototxt/yolov4-leaky-test.prototxt save caffemodel to caffemodel/yolov4-leaky-test.caffemodel
Do you know the reasons why when I run nnie mapper ./yolov4.cfg,the result is begin net parsing.... end net parsing begin prev optimizing.... Segmentation fault (core dumped)
> @antran89 i am sorry,,now I've solved the problem ,,thank you 您好，怎么解决的
@CasonTsai 您好，请问怎么解决的
loaded weights from weights/converted.weights let's test the original model first: Class Images Targets P R mAP F1: 0%| | 0/174 [00:00
` percent_limit = (sorted_bn==highest_thre).nonzero(as_tuple=False).item()/len(bn_weights) ValueError: only one element tensors can be converted to Python scalars `
prune_util.py ` mask = CBLidx2mask[route_in_idxs[0]] KeyError: 108 `