Errors running mmimdb examples

[Sudhendra]

First off, grateful for the repo and hats off to the tremendous effort that went into building this.

When experimenting with one of the given examples "MultiBench/examples/multimedia/mmimdb_simple_early_fusion.py". There are multiple errors being faced.

1. The files vgg.tar, synset_words.txt and GoogleNews-vectors-negative300.bin.gz are required to run the function at from datasets.imdb.get_data import get_dataloader and to initialize the class at from .vgg import VGGClassifier. These are locally passed from the authors' source code but are not available in the git repo. This makes it hard for developers like me to run tests and experiment with the repo.

I would also want to point out that installation of the package blocks isn't available in the environment.yml file so that had to be installed separately. If possible please, share the above files so I can run experiments for my project as well.

[yuquanqingyin]

First off, grateful for the repo and hats off to the tremendous effort that went into building this.

When experimenting with one of the given examples "MultiBench/examples/multimedia/mmimdb_simple_early_fusion.py". There are multiple errors being faced.

1. The files vgg.tar, synset_words.txt and GoogleNews-vectors-negative300.bin.gz are required to run the function at from datasets.imdb.get_data import get_dataloader and to initialize the class at from .vgg import VGGClassifier. These are locally passed from the authors' source code but are not available in the git repo. This makes it hard for developers like me to run tests and experiment with the repo.

I would also want to point out that installation of the package blocks isn't available in the environment.yml file so that had to be installed separately. If possible please, share the above files so I can run experiments for my project as well.

I have the same problem, did you solve it?

[leethologica]

Bumping this in hopes one of the authors happens to see this. There are many local paths used throughout this repository in general that makes it difficult to reproduce experiments or run the example scripts.

GoogleNews-vectors-negative300.bin.gz can be downloaded via Kaggle, but it is unclear to me where the other files (synset_words.txt and vgg.tar) could be found.

Furthermore, blocks is a rather outdated package and am looking to reproduce the IMDB experiments using (or basing off of) an off-the-shelf VGG16 network from PyTorch or some other source, but it is difficult to do this without being able to replicate the baseline experiment.