Course 4 week 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi, doing multiclass image classification

#when I run this on google colab:
initial_epochs = 2

history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=initial_epochs)

#getting error:

Epoch 1/2
259/496 [==============>…] - ETA: 2:55 - loss: 4.7895 - accuracy: 0.1194

InvalidArgumentError Traceback (most recent call last)
in ()
1 initial_epochs = 2
----> 2 history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=initial_epochs)

1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
57 ctx.ensure_initialized()
58 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
—> 59 inputs, attrs, num_outputs)
60 except core._NotOkStatusException as e:
61 if name is not None:

InvalidArgumentError: Invalid GIF data (size 77719), failed to slurp gif file: Failed to read from given file
[[{{node decode_image/DecodeImage}}]]
[[IteratorGetNext]] [Op:__inference_train_function_15482]

can anyone please solve this issue ?

2

If you are running this in a different environment than the course website (Google Colab in this case), then it is your problem to make sure that you have brought over all the required files, not just the notebook. And to have situated them in such a way that the notebook logic can find them. That may not work the same way on Colab as it does on the Coursera website, right?

This is beyond the scope of the course: if you want to play this kind of game, then you need to have the problem solving skills to figure out this type of issue. The mentors are unpaid volunteers who are here to answer questions about the course materials, not to be your IT support staff for getting things to work on Colab.

Don’t get me wrong: it’s fine to post a question like this. Maybe you get lucky and one of your fellow students knows the answer. Or maybe one of the other mentors is a nicer person than I am. I’m just saying that I don’t personally feel like I owe you an answer to this question. And this is a rabbit hole, right? What’s the next problem?