gabarlacchi

Apply GradCam to Cnn+LSTM

2

Hi all, I am working with a feature extractor (Inception V3, VGG16, whatever) plus an LSTM for sequences classification (let's say 3 sec. each one). There's any way to use...

Explain CNN+LSTM Classification

3

Hi! I am developing a clip classificator using features (extracted from a CNN) fed into an LSTM for classification. It's an end-to-end system. I would like to know if it's...

Hello, Thank for the work, very useful. I am using a network like: CNN (feature extraction) + LSTM (sequence classification) and I would like to apply tf-explain to it. Is...

Apply darkon to CNN+LSTM

1

Hello, nice work, i really appreciate it. I would like to know if it's possible to apply the idea of gradCam to a network such: pre-trained CNN for feature extraction...

Inference on videos gives black gazemap

6

Hello, I am trying to implement your work as baseline, but when I run the inference on my own data it gives output black images. I followed the steps described,...

Best practice to update interactions with an existing dataset

2

Hi there! Thanks for the nice work in RecBole! I'm implementing a simulation system in which I generate interactions between users and items within an existing system. At the start...

[🐛BUG] Not clear how to implement user item knn (collaborative filtering user based)

1

We used item_KNN model and get fine results. We tried to implement user based version, because the code seems ready to be used for that purpose. But just passing the...

[💡SUG] Consider interactions frequency and not ratings

1

Hey there, thanks for the amazing work here. I would like to fully understand how to load a dataset (which also contains ratings value for each interaction) by considering the...