kinoc

+1, similar circumstance. Upgrade/rebuild of OS from 16.04 to 18.04 LTS, python 3.6.8 , working my way through getting my app up back to a running state, and got this...

Edit __init__.py around line 315 which in my system is ~/.local/lib/python3.6/site-packages/language_check/__init__.py line 315: @classmethod def _get_root(cls, url, data=None, num_tries=2): url=url+"/Languages" for n in range(num_tries): Adding that line seemed to get...

@soumith @SaMnCo Any luck? I have similar problems trying to build with my TX1, and the process dies at the same point after loading the 3GB ascii file.

I made a "convert_ascii_to_arm.lua" file for the TX1 that just loads the ascii model then writes out the binary "ntalk2.arm.t7" file. I then can use the unaltered eval.lua on "ntalk2.arm.t7",...

Thanks for the patch @soumith I applied mvittorch7 and the patch and got the following results (note: "evalp.lua" is "eval.lua" with the patch applied) ``` ubuntu@tegra-ubuntu:~/neuraltalk2$ th evalp.lua -model /home/ubuntu/neuraltalk2/models/model_id1-501-1448236541.t7...

I am running on a Nvidia TX1. I have CUDA 7.0 installed. In ~/cudnn there is cudnn-7.0-linux-ARMv7-v4.0-rc1.tgz along with the v4.0_rc1 release notes, and ~/cudnn/cudnn.h says basically 4.0.2. Does that...

@soumith Thanks, problem solved! So summary for TX1 users: apply patch in https://github.com/karpathy/neuraltalk2/issues/32#issuecomment-162134615 and use the R4 bindings listed above

One follow on. What would the change (if any) be for "train.lau"? I was trying a small test set of 100 train and 100 test images just to learn the...

@soumith I hear you (about using the TX1 for training). Unfortunately I don't have a native Linux box setup. I do have everything setup and working fine in a x86...

@soumith ok, no rush. There are plenty of other areas to work on. Thanks and good luck with NIPS!