search

ceccocats / tkDNN

Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms
GNU General Public License v2.0
718 stars 209 forks source link

Segmentation fault (core dumped) #169

Closed tim94173 closed 3 years ago

tim94173 commented 3 years ago

I run ./darknet export <cfg> <weights>but it show

nms_kind: greedynms (1), beta = 0.600000 Total BFLOPS 10.903 avg_outputs = 276828 Allocate additional workspace_size = 19.66 MB Loading weights from backup/yolov4-tiny3l-test1_16000.weights... seen 64, trained: 1024 K-images (16 Kilo-batches_64) Done! Loaded 50 layers from weights-file n: 0, type 0 Convolutional weights: 864, biases: 32, batch_normalize: 1, groups: 1 write binary (null)/c0.bin Segmentation fault (core dumped)

how can i fix it?

thnkinbtfly commented 3 years ago

I think you missed the instructions. If you do mkdir and add another argument, I think it will be resolved.

mkdir layers debug
./darknet export <path-to-cfg-file> <path-to-weights> layers

https://github.com/ceccocats/tkDNN#1export-weights-from-darknet

tim94173 commented 3 years ago

I am an idiot , I forgot enter "layers" haha...

mive93 commented 3 years ago

Closing for now, feel free to reopen.