Make an AI sound like a YouTuber (LAB): Crash Course AI #8
video description
Date: 2022-04-04
Related videos
Comments and reviews: 10
scm6079
This is how you can fix the Runtime error on Step 3. 3 (shape invalid):
In step 3. 1 there is a line that reshapes the tensor prediction_vector. The problem is that the view function, which is meant to reshape the tensor, in step 3. 1 is not being adjusted properly. If there is any situation that you don't know how many rows you want but are sure of the number of columns, then you can specify this with a -1. Only one of the axis values can be -1! This is a way of telling the library: -give me a tensor that has these many columns and you compute the appropriate number of rows that is necessary to make this happen-.
Thus, the fix to this error is to go into Step 3. 1, find line #11, which looks like:
prediction_vector = prediction_vector. view(seq_len - batch_size, -1)
and change this to be:
prediction_vector = prediction_vector. view(-1, len(vocabulary)
Letting the first dimension auto-size, and the second dimension be equal to the size of our vocabulary.
reply
This is how you can fix the Runtime error on Step 3. 3 (shape invalid):
In step 3. 1 there is a line that reshapes the tensor prediction_vector. The problem is that the view function, which is meant to reshape the tensor, in step 3. 1 is not being adjusted properly. If there is any situation that you don't know how many rows you want but are sure of the number of columns, then you can specify this with a -1. Only one of the axis values can be -1! This is a way of telling the library: -give me a tensor that has these many columns and you compute the appropriate number of rows that is necessary to make this happen-.
Thus, the fix to this error is to go into Step 3. 1, find line #11, which looks like:
prediction_vector = prediction_vector. view(seq_len - batch_size, -1)
and change this to be:
prediction_vector = prediction_vector. view(-1, len(vocabulary)
Letting the first dimension auto-size, and the second dimension be equal to the size of our vocabulary.
reply
crash_course
I hope someone compiles a super data set of every word John Green has ever written and spoken online: his books, vlog brothers, brotherhood 2. 0, crash course, twitter, commencement speeches, tour speeches, hacked personal emails, etc.
reply
I hope someone compiles a super data set of every word John Green has ever written and spoken online: his books, vlog brothers, brotherhood 2. 0, crash course, twitter, commencement speeches, tour speeches, hacked personal emails, etc.
reply
frmcf
I know this is just an exercise, but part of what makes John Green sound like John Green is his use of infrequent words like -whippersnapper- (not that infrequent, perhaps) and original coinages like -zombicorns-. How could you program that?
reply
I know this is just an exercise, but part of what makes John Green sound like John Green is his use of infrequent words like -whippersnapper- (not that infrequent, perhaps) and original coinages like -zombicorns-. How could you program that?
reply
Andy
If you want the AI to produce -interesting- sentences, it not only needs a model of what is possible to say, it needs a model of the listener, so it knows how acceptable they might find -totes amazeballs- and -Lilliputian-.
reply
If you want the AI to produce -interesting- sentences, it not only needs a model of what is possible to say, it needs a model of the listener, so it knows how acceptable they might find -totes amazeballs- and -Lilliputian-.
reply
Danilego
What an amazing video! The program was great to follow along and produced some really funny results. Jabril was a fantastic host as always, I laughed so hard at -totes amaze. balls. - 5: 50 hahaha so good!
reply
What an amazing video! The program was great to follow along and produced some really funny results. Jabril was a fantastic host as always, I laughed so hard at -totes amaze. balls. - 5: 50 hahaha so good!
reply
Ossi_Petter1
-Lexical types occuring more thEn n times- is -then- an acceptable alternative to -than- nowadays? Eng is my second language so I don't really know if that's the case. Because I see it a lot
reply
-Lexical types occuring more thEn n times- is -then- an acceptable alternative to -than- nowadays? Eng is my second language so I don't really know if that's the case. Because I see it a lot
reply
Mikerhinos
Be careful because in EU we now have to deal with RGPD and the voice is a personnal data so you can't use someone's voice to train your model without an autorization. :(
reply
Be careful because in EU we now have to deal with RGPD and the voice is a personnal data so you can't use someone's voice to train your model without an autorization. :(
reply
frmcf
I wrote this before I was going on the road and then I-m not doing that the time of time and then maybe I should go get a ride and get my stuff to get to my truck.
reply
I wrote this before I was going on the road and then I-m not doing that the time of time and then maybe I should go get a ride and get my stuff to get to my truck.
reply
Captain
5: 25: So. did anyone else notice that one of the words in Human John Green's list is -bull---t-, or was that just me? Asking for my imaginary friend. :D
reply
5: 25: So. did anyone else notice that one of the words in Human John Green's list is -bull---t-, or was that just me? Asking for my imaginary friend. :D
reply
William
All those crash courses are FUN with Knowledge. But you should develop an Android App with a library of the courses. Thus we can listen and study them!
reply
All those crash courses are FUN with Knowledge. But you should develop an Android App with a library of the courses. Thus we can listen and study them!
reply
Add a review, comment
Other channel videos
