官术网_书友最值得收藏!

Visualizing losses

To visualize the losses for the training, start the tensorboard server, as follows:

tensorboard --logdir=logs

Now, open localhost:6006 in your browser. The SCALARS section of TensorBoard contains plots for both losses:

Loss plot for the generator network
Loss plot for the discriminator network

These plots will help you to decide whether to continue or stop the training. If the losses are not decreasing anymore, you can stop the training, as there is no chance of improvement. If the losses keep increasing, you must stop the training. Play with the hyperparameters and select a set of hyperparameters that you think might provide better results. If the losses are decreasing gradually, keep training the model.

主站蜘蛛池模板: 城固县| 双江| 东平县| 宁波市| 定安县| 商水县| 富民县| 衡阳县| 西华县| 西丰县| 四子王旗| 台北县| 宣汉县| 敦化市| 怀柔区| 南雄市| 健康| 聊城市| 宣城市| 苍溪县| 刚察县| 新乡市| 洪雅县| 安远县| 衡山县| 榆中县| 赫章县| 西昌市| 蓝田县| 泰兴市| 临城县| 西宁市| 平阴县| 城步| 介休市| 通化县| 江源县| 禹州市| 日土县| 天柱县| 梁平县|