ReDNA Labs comments

Results 8 comments of


                                            ReDNA Labs

Publish number of parameters for each task

After running the JAX code and using the structure information in the research paper, I obtain the following number of parameters for each task: ListOps: 19.9M Text: 3.5M Retrieval: 1.087M...

DAIN: "no kernel image is available for execution on the device"

for issues related to : correlation_forward_cuda , I managed to make it work by setting: by setting nvcc '-gencode', 'arch=compute_70,code=compute_70' GTX 2080Ti python 3.7 torch 1.4 cuda 10.0 reference: [https://github.com/baowenbo/DAIN/issues/44](https://github.com/baowenbo/DAIN/issues/44)...

where the X_test_408.npy?

Same issue here. Where can the file X_test_408.npy be downloaded from. Thanks in advance

where the X_test_408.npy?

Hello, this is the training file which contains X_train_408.npy, but how about the test file: X_test_408.npy ? thanks

where the X_test_408.npy?

Ah yes I was just wondering if you had the npy file ready, but nevermind I will build it from the text file. Thanks for your assistance. Have to say...

where the X_test_408.npy?

I was expecting the file: X_test_408.npy to be found next to X_train_408.npy I can see that it is possible to build it from scratch by reading the text file, but...

where the X_test_408.npy?

appreciate it, thanks

where the X_test_408.npy?

Hello, I have tried to reconstruct the missing X_test_408.npy file from test.txt, but the results when training the algo do not match the expected. It only gets about 56% test...