a790399215
a790399215
例如：藏UPXSGW车牌被识别成：藏PPPPPP
后面六个字符的识别结果基本是一样的
test_nn.py代码如下： `import numpy as np import pickle from keras.layers import Dense, Input, BatchNormalization, Conv2D, Flatten, MaxPooling2D, Activation, Reshape, Layer from keras.models import Model, load_model, model_from_json from keras.callbacks import TensorBoard, ModelCheckpoint,...
想请教一下，我运行create_traindata生成了5000张图片，batch_size是256训练了20轮，但是在运行test_nn.py文件输出的结果却是完全错误的，想请教一下大家有遇到这种情况吗
例如：藏UPXSGW车牌被识别成：藏PPPPPP，后面六个字符的识别结果基本是一样的
test_nn.py代码如下： `import numpy as np import pickle from keras.layers import Dense, Input, BatchNormalization, Conv2D, Flatten, MaxPooling2D, Activation, Reshape, Layer from keras.models import Model, load_model, model_from_json from keras.callbacks import TensorBoard, ModelCheckpoint,...
Yeah,because the time you run is too short. I run the code for a whole night,the recognized result was fine. | | buptwanghao | | 邮箱：[email protected] | Signature is customized...
Yeah,train the model as long as possible.You can try to run the code before you sleep,and check the performance when you get up. | | buptwanghao | | 邮箱：[email protected] |...