in the chart5 CNN implementation parts, we separate the dogs pictures into training data(80%) and testing data (20%), what is the loss value after 100000times training (if we follow the default setting?), how can we evaluate this CNN module(accuracy and how to use the training model )? who can share the rest demo code or some running result(including the write summary to tensor board graph event)?
in the chart5 CNN implementation parts, we separate the dogs pictures into training data(80%) and testing data (20%), what is the loss value after 100000times training (if we follow the default setting?), how can we evaluate this CNN module(accuracy and how to use the training model )? who can share the rest demo code or some running result(including the write summary to tensor board graph event)?