Trilok Padhi comments

Results 7 comments of


                                            Trilok Padhi

Weird tryon results after running CP-Viton-plus on colab - am I doing something wrong!

Hi @minar09 At first , I tested the model with the test images you had given , the results are really really good , appreciate you for the awesome work...

Error while running demo.sh "view size is not compatible with input tensor's size and stride"

hey can you try changing that line to x = x.contiguous().view(x.size(0), -1) it worked for me Thanks

NodePiece Model takes more time to process the data when we use a subset of training data

Hi @mberr Thanks for your reply. Just to highlight the difference, The pipeline definition in the **code block 1** creates anchor nodes faster than the **code block 2**, The **code...

NodePiece Model takes more time to process the data when we use a subset of training data

Hi @mberr, Not really, the time taken to create the anchor nodes from the dataset in the pipeline function basically

NodePiece Model takes more time to process the data when we use a subset of training data

Hi @cthoyt Thanks for your reply. Before I test the time, the issue is the code is getting stuck ( I waited for 6 hours ) when I create the...

NodePiece Model takes more time to process the data when we use a subset of training data

@cthoyt @mberr could you please look at this issue ? Thanks

Is there a way to prevent llama2 from truncating the answer at the middle of sentence when it reaches the maximum token length?

The following worked for me to prevent llama2-7b-chat-hf to stop at the middle of sentences and use special tokens [ 2277, 29937 ] ``` class EosListStoppingCriteria(StoppingCriteria): def __init__(self, eos_sequence=[2277, 29937]):...