Yolov4 Tiny Training error

I’m training yolov4_tiny with cml:

docker run -it --rm --ipc=host --ulimit memlock=-1 --ulimit stack=67108864\
        --gpus device=2 \
        -v /home1/data/hungpham/TaoToolKit/Detectnet_v2/experiment:/yolov4_tiny \
        nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5 /bin/bash  \
        OMP_NUM_THREADS=4 yolo_v4_tiny train \
        -r /yolov4_tiny/result_yolov4_tiny \
        -e /yolov4_tiny/result_yolov4_tiny/config_yolov4_tiny.txt \
        --log_file /yolov4_tiny/result_yolov4_tiny/log_training_terminal_v3.txt \
        -k yolov4_tiny_crn

But model fault, here my log train and config traning:

numpy.core._exceptions.UFuncTypeError: ufunc 'add' did not contain a loop with signature matching types (dtype('float64'), dtype('<U1')) -> None

log_training_terminal_v3.txt (55.7 KB)

config_yolov4_tiny.txt (2.8 KB)

1 post - 1 participant

Read full topic