Section 02: Facing the error TypeError: __new__() missing 1 required positional argument: 'task'

[karthikbhandary2]

Hello

I am getting the following error. I looked it up on the net and found that I need to pass an argument. I tried giving it the argument as 'multiclass' but it is leading to an AssertionError. Help would be great!

[PatTheAtak]

Could you post your code of Accuracy()

[mrdbourke]

Hey @karthikbhandary2,

Good question!

There's been an update to TorchMetrics since the video was recorded.

Please see the fix here: #200 (comment)

Or alternatively, you can try:

try:
    from torchmetrics import Accuracy
except:
    !pip install torchmetrics==0.9.3 # this is the version we're using in this notebook (later versions exist here: https://torchmetrics.readthedocs.io/en/stable/generated/CHANGELOG.html#changelog)
    from torchmetrics import Accuracy

# Setup metric and make sure it's on the target device
torchmetrics_accuracy = Accuracy(task='multiclass', num_classes=4).to(device)

# Calculate accuracy
torchmetrics_accuracy(y_preds, y_blob_test)

[karthikbhandary2]

Thank @mrdbourke for the response. I've looked up the #200 fix and I've done exactly as it was told there and my code is working now.