Table 1 Division and statistics of the training and test sets in the MTACCR dataset
From: HUNet: hierarchical universal network for multi-type ancient Chinese character recognition
MTACCR dataset | Category | Data volume | Imbalance factor | Source | |||
|---|---|---|---|---|---|---|---|
max/min | mean | Std deviation | |||||
Training Set | 7874 | 7,423,379 | 10,178 | 942 | 1069 | Other data sources | |
Test Sets | Test_1 | 7638 | 600,844 | 100 | 78 | 27.8 | |
Test_2 | 6432 | 390,337 | 100 | 60 | 34.4 | ||
Test_3 | 4926 | 275,788 | 100 | 55 | 35.4 | ||
Test_4 | 3629 | 214,612 | 100 | 59 | 33.4 | ||
Test_5 | 3023 | 177,632 | 100 | 58 | 32.7 | ||
