linjian

从报错来看，问题很明显，run_batch 函数返回值的数量和调用 run_batch 函数时赋值的变量个数不匹配。至于 loss_x ... 的图像如何画，保存训练过程中的 loss 数据，后处理时画图即可。

这是 KITTI 提供的每帧图片的真值位姿数据，具体内容可以从官网下载。

@TimothyLiuu 首先很高兴能关注到这个工作，当时开源代码未考虑周到，项目也不再维护。建议在理解实现原理的基础上，用新的 pytorch 版本重构代码。

@StaticTemp Hi, could you locate the specific lines of '../data/Train.json', '../data/Validation.json' and '../data/metadata.tsv' in my code. Meanwhile, the dataset are download from Kaggle "toxic comment classification" competition. Best wishes.

I have sent the model_90000.ckpt file to your email. Please remember to check.

You should change the model path to your own path where the model_90000.ckpt locate. And I have sent "mean_var_out.npz" file to you attached in the last email, it contained the...

Firstly, make sure that you have add `self.mean_var = [mean1,var1,mean2,var2,mean3,var3,mean4,var4,mean5,var5,mean6,var6,mean7,var7,mean8,var8]` in the CNN model. And use `mean_var = net.mean_var` to get the variables in main function. Secondly, you can save...

@javimol You can read `train_mycnn.py` carefully to understand what it does firstly. Then you should prepare the dataset and tensorflow environment. Finally, run the code and get the model. The...

Thanks for your notice of my code. I have added a MIT licence, just use it freely~