Mattia Soldan

I have the same problem, have anyone found a solution?

Dear @NeverMoreLCH thank you for reaching out. Kindly provide me with a snapshot of your environment and the command you are using to train the models. I will try and...

Dear @NeverMoreLCH I apologize for the delay. I verified that I could reproduce evaluation and training on my side using my environment. I was not able to easily install the...

Dear @NeverMoreLCH I notice from the logs that the loss is decreasing while the performance in evaluation is stable and not changing. Moreover, such performance are on par with random...

Hi @tujun233 I am currently out of office so I cannot delve into the code right now. - Did you try reducing the learning rate as suggested? - Otherwise if...

Dear @tujun233 I apologize for the inconvenience. I will reach out with a solution as soon as I am back in the office. Just to make sure: - Are you...

Dear @tujun233 that is great news indeed. You might need to run hyperparameters search on the learning parameters now that you bumped down the batch size. Please feel free to...

Hi @tujun233 , yes, Activitynet videos are publicly released. Check this [link](http://activity-net.org/download.html) for the official Activitynet dataset webpage. Activitynet Captions (dataset used in this repo) is built upon the Activitynet...

Hi @huxiwen please check [this](https://github.com/Soldelli/VLG-Net/issues/3) other thread. I provide the code for computing the syntactic dependencies in each sentence. Let me know if you have any issues running it. Best,...

Dear @jianhua2022, kindly look into the documentation of the spacy library to obtain them. [This](https://spacy.io/api/dependencyparser) is a good starting point. I looked for the script we used during the VLG-Net...