InvalidArgumentError

[mikechen66]

simSiam.ipynb Self-supervised contrastive learning with SimSiam

While I run the simsiam on Colab T4 16G graphical memory , ther is the error as follows. Please help handle the issue.

InvalidArgumentError Traceback (most recent call last) in <cell line: 23>() 23 for n in range(25): 24 ax = plt.subplot(5, 5, n + 1) ---> 25 plt.imshow(sample_images_one[n].numpy().astype("int")) 26 plt.axis("off") 27 plt.show()

1 frames /usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name) 6654 def raise_from_not_ok_status(e, name): 6655 e.message += (" name: " + str(name if name is not None else "")) -> 6656 raise core._status_to_exception(e) from None # pylint: disable=protected-access 6657 6658

InvalidArgumentError: {{function_node wrappedStridedSlicedevice/job:localhost/replica:0/task:0/device:GPU:0}} slice index 8 of dimension 0 out of bounds. [Op:StridedSlice] name: strided_slice/

[SuryanarayanaY]

Hi @mikechen66 ,

The tutorial works fine with TF2.13 on colab GPU environment. Please refer attached gist.

Either it might have fixed already or you might be changing some changes to the code that causing out of bounds error.

Could you please verify the gist and confirm? Thanks!

[github-actions[bot]]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

[github-actions[bot]]

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.