Jisheng Yin

icon company University of Chinese academy of science icon location Beijing icon location Major in artificial intelligence,especially in deep reinforcement learning.welcome anyone communicate with me in computer science

Results 17 comments of Jisheng Yin

AttributeError: 'NoneType' object has no attribute 'get_current_context'

> Are you referring to the next MuJoCo release as the future version of MuJoCo or is the version I am currently using too old. I have the similar error...

tensorflow.python.framework.errors_impl.AbortedError: All 10 retry attempts failed. The last failure: Error executing an HTTP request: libcurl code 42 meaning 'Operation was aborted by an application callback', error details: Callback aborted

![cizhi3 jpg2e6bd73cd258d12d78aaebe059794d59](https://github.com/google-research/kubric/assets/110964890/988e060b-55cb-4f35-b02f-9a14d151689a) this is the full info of the error

麻烦将zlib的官网更新为singlelogin.re

> 现在改成这个了：https://zh.zlibrary-global.se/ 这个现在也不行了， 唉

_pickle.UnpicklingError: Failed to interpret file '../checkpoint/checkpoint.npy' as a pickle

> Did you find a solution? Running into the same error. I solved the error by changing a model.Notably, the model in readme is a tapnet baseline model, which has...

ValueError: All `hk.Module`s must be initialized inside an `hk.transform`

> Yup, forgot that even the tapir constructor needs to be called inside a haiku transform. I've attached a working verson of this script, but it's a bit ugly; we...

ValueError: All `hk.Module`s must be initialized inside an `hk.transform`

> Yup, forgot that even the tapir constructor needs to be called inside a haiku transform. I've attached a working verson of this script, but it's a bit ugly; we...

ValueError: All `hk.Module`s must be initialized inside an `hk.transform`

> Yes, if you want to track across videos, we recommend that you have separate forward passes to extract features and to perform tracking; the model hasn't seen cuts during...

ValueError: All `hk.Module`s must be initialized inside an `hk.transform`

> Yes, if you want to track across videos, we recommend that you have separate forward passes to extract features and to perform tracking; the model hasn't seen cuts during...

ValueError: All `hk.Module`s must be initialized inside an `hk.transform`

> The tracks on your demo look pretty reasonable to me, which suggests you're using the code correctly. > > It looks like the objects are oriented differently between the...

ValueError: All `hk.Module`s must be initialized inside an `hk.transform`

> The tracks on your demo look pretty reasonable to me, which suggests you're using the code correctly. > > It looks like the objects are oriented differently between the...