Training custom data with tfrecord is error?

[doandv-java]

I run :python train.py --dataset ./data/head_train.tfrecord --val_dataset ./data/head_val.tfrecord --classes ./data/data.names --num_classes 1 --mode fit --transfer darknet --batch_size 16 --epochs 10 --weights ./checkpoints/yolov3.tf --weights_num_classes 80. Then result :tensorflow.python.framework.errors_impl.FailedPreconditionError: {{function_node _inference_Dataset_map_12618}} Table not initialized. [[{{node hash_table_Lookup/LookupTableFindV2}}]] [[IteratorGetNext]]

[kalikhademi]

I have the same problem to train it with the tfrecord files of my custom dataset. Does anyone know any solution?