I have error on grader like this:
Failed test case: Layer is different than expected.
Expected:
[‘Dense’, (None, 128, 4), 132, ‘log_softmax’],
but got:
[‘Dense’, (None, 128, 4), 132, ‘log_softmax_v2’].
This is my code:
!removed by moderator
Actually, the test is passed but got error in grader"
Please help me
Try activation=tf.nn.log_softmax (not `activation=‘log_softmax’)… TensorFlow…
Cheers
How do you update to new labs ? I still have trax notebooks.
Hi @sapiensush
I don’t really know. I would try the regular “Help” → “Get latest version” but if that doesn’t help, please contact the Staff.
Check out this discussion it might also help (I personally did not follow it).
Cheers
Actually Get Latest version doesnt work even after deleting the notebooks.
Understood @sapiensush. I actually don’t know then, since I have not received any instructions how to handle this transition.
Hi @sapiensush, To update to the new TensorFlow labs just go the home page of your course, and click on the three horizontal dots at the top right. Then select Join Session. You can then select a session that starts from today’s date. Mind you, you’ll lose all your progress and all your labs will be gone. Make sure you have them saved.
Hi Lukman,
I dont understand this. The three dot menu only appears on the homepage of completed courses. And tensorflow upgrade is available only for course 3 and 4 of nlp.
On top of that, I did that join session for course 1 only because that is where only it comes.
What is the proceduee for the courses in progress ?
I keep getting too many requests message for some reason for accessing coursera.
Thanks,
Sushant
Oh. I forgot. Yes, this is for completed courses. For courses in progress, you need to reset the deadline so that it switches you to another schedule automatically. This will come with the new labs.
So, if you are taking courses 3 and 4 at the moment, the easiest way is to miss some assignment deadlines and reset it to get the new labs. Your progress will be lost though.
Maybe there is a faster way, I do not know it yet.
self.dense = tf.keras.layers.Dense(vocab_size, activation=tf.nn.log_softmax, name=‘log_softmax’)
You need to define the name of this activation and it worked really well
