Fin Amin comments

Results 13 comments of


                                            Fin Amin

NameError: name 'args' is not defined

I am having the same issue

NameError: name 'args' is not defined

A workaround is to edit the build_rawframes.py file and hardcode wherever the args variable is used. For example, before: `out_full_path = args.out_dir #on line 29 ` after: `out_full_path = r'C:\path\to\mmaction2\data\ucf101'`

Add try-catch logic to handle image loading failure in LoadImageFromFile

I am submitting a pull request in order to fix this!

Predict the trained model

> There is a `get_test_generator()` which returns a test generator. You need to use `split_test` argument in constructor call to give the proportion of test data, it works like `split_val`...

tf.Keras and shap.Explainer fail with shap v0.37

Still having this issue :(

Fixed an incorrect numerical comparison in numbers.py

Looks good to me. Nice catch.

Fail to install MXNet with cu110

Having identical issue

Generate score based on a single node instead of aggregating the whole graph

I might be misunderstanding what you're asking. Are you asking how to get a node level prediction? Because that is explained in the docs. If you're trying to get the...

Generate score based on a single node instead of aggregating the whole graph

Is there a way you can mask the other node embeddings with a 0 or some dummy variable? That way your pooling layer only gets the value from your important...

Generate score based on a single node instead of aggregating the whole graph

"Since when building a model via subclassing tensorflow runs without eager excecution, I can't use eager functions to check the values of the index tensor that indicates which graph each...