fangxu

thanks , I have resolve it with resize the input image to (512,512).....

I get this problem ``` 'default': {'frequent': 20, 'kvstore': 'device'}, 'gpus': '0', 'network': {'ANCHOR_RATIOS': [0.5, 1, 2], 'ANCHOR_SCALES': [4, 8, 16, 32], 'FIXED_PARAMS': ['conv1', 'bn_conv1', 'res2', 'bn2', 'gamma', 'beta'], 'FIXED_PARAMS_SHARED':...

@xingbowei 还没解决呢..运行python demo.py 也有问题l..

@xingbowei python demo.py 已经跑通了，这个错误好像对后面的运行没什么影响

@AdamAsh2019 嗨 大佬，你好，那个VINET 你的训练接有收敛吗？想跟你 讨论一下 关于最后的SE3 位姿累积

I also have this problem. how to run lsd-slam with omni camera ~~do you resolve this? Who can give me some help? ~ thanks very much @baozeng90 @EnriqueSolarte @christiankerl @pierriko...

@SummerIcequeen @ffurrer @lesire

@jacksonkr

理解了，没有错误，但是权重如果不放在 conv caps 类的初始化里面 ，可能更好理解一点。但是这样写更紧凑 

@ChiWeiHsiao @lucleon Hi , I have same questions.