1 | initial version |
i got it running using the pbtxt from here , but you'll probably need to update your opencv libs to latest master
(also, the uint8 model has significantly less accuracy)
2 | No.2 Revision |
i got it running using the pbtxt from here , but you'll probably need to update your opencv libs / cv2 to latest master
(also, the uint8 model has significantly less accuracy)
3 | No.3 Revision |
i got it running using the pbtxt from here , but you'll probably probably need to update your opencv libs / cv2 to latest master
(also, the uint8 model has significantly less accuracy)
4 | No.4 Revision |
i got it running using the pbtxt from here , but you'll probably need to update your opencv libs / cv2 to latest master
(also, (then, the uint8 model has significantly less accuracy)accuracy, so i'd also recommend to stick with the fp16 caffemodel and your current codebase for now)