Gianluca Guzzetta
Gianluca Guzzetta
Hi, you could try by adding and creating an ad hoc `.csv` file storing your predictions in a dataframe. If you want some help, you might share your snippet code...
If you want, I can still arrange in a better way the code, aiming at realizing a custom torch loss, would you like to update the code together or can...
Hello dude, as far as I understood, you want to use pretrained model weights (which you can find from the model zoo regarding the selected model chosen for inference), and...
My suggestion, if you using a conda environment, is to install the base environment as described, and insert the new required packages in this form 'pip install / conda install',...
Any resolution to this task? Any exported model using self.attention is leaking this, hence no dynamic shapes cannot be used for seq_length! Thanks
Okay thanks, do you know if mmc is not evaluated in the script, even if it active (for now i am using the single image predictor), so for now no...
Okay that was since I had a mmc license for the Stream product. How can I use that license and in which script to avoid making usage of snapchat sdk...
But can I use my api key and license in this repo for the stream or not? The container containes encrypted python files, that was my question, thanks