2017TJMtaotao

损失特别大有啥优化策略吗

1

Epoch 38/50 4/4 [==============================] - 10s 2s/step - loss: 92487.3184 - val_loss: 75600.4219 Epoch 39/50 4/4 [==============================] - 10s 3s/step - loss: 89534.9199 - val_loss: 63017.3125 Epoch 40/50

Thank you for open source！ How can I get the default anchor box for my new data? Look forward to your reply。

关于数据集所用的标注工具

1

我看代码是采用四点标注，请问大佬用的标注工具是什么，还有标注过程种的注意事项

AttributeError: module 'tensorflow.tools.api.generator.api.estimator' has no attribute 'SessionRunHook'

ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshape') with input shapes: [1,1,1,64], [].

2

ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshape') with input shapes: [1,1,1,64], [].