Комментарии:
Thank you :)
ОтветитьWhat are the prerequisites for this course?
ОтветитьNice tut, but I's like to mention that this is a tuto, it's meant to teach sth. It would be nice if it was a bit slow paced.
ОтветитьPlease how do I get the data set
And where do I get it from
Hoped see not-api tensorflow. Well, good tutorial for begginers, ty!
ОтветитьDONT WATCH THIS TUTORIAL FIRST ELSE YOU WILL CONFUSE THE CRAP out of your self ................ come back and watch this tutorial when you have watched 5 tf tutorials from else where ...
ОтветитьMy biggest problem with the TensorFlow guidelines is that there is no direct instruction on how to use your own data. The official TensorFlow guidelines do not clearly address all the requirements. I have also wondered why, for example, it is made so difficult to convert text into a TensorFlow-compatible data format.
The official TensorFlow guidelines say "load CSV data" is a good example. The first section is really clear and simple when measuring the size of a clam or whatever it is. In the second section explaining the survivors of the Titanic the data conversion to a format suitable for TensorFlow is a pain in the ass. Why hasn't TensorFlow done anything to alleviate this.
Great tutorial! One question about the globalaveragepooling layer. After embedding we are actually taking the average of the embedding features over all the word vectors and not the average of every individual vector? Say we have 2 words in a sentence that we want to predict the sentiment of: "Very nice" -> [1,1,1,1], [2,2,2,2] -> 2 words, 2 word vectors with 4 embedding features (contexts). The correct way is to take the average over these vectors so the lower dimensional output is [1.5, 1.5, 1.5, 1.5], that we then pass to the dense layer. And the incorrect way is to output a 2 dimensional vector averaging the 2 vectors individually -> output: [1, 2]? Just averaging every word vector individually and passing every single one in a new vector doesn't make sense to me and would just throw away the context.
ОтветитьDoes this course teach Keras in Tensorflow, or pure Tensorflow only?
ОтветитьI feel like this was a Keras tutorial
ОтветитьThanks for making this insightful video. One quick question, when flattening the data, shouldn't we expect 28 by 28 by 3 values for each image given that each pixel is represented by three RGB values?
ОтветитьCorrect me if I'm wrong but I think each neuron (each layer to be precise) has 1 bias parameter, rather than 4 as in the example above.
ОтветитьMust watch for basics of TensorFlow. Good Tutorial
ОтветитьJust use Jupyter notebook then you don't have to keep re-training the model everytime you want to run the code.
Ответитьany one clear me about this error ::: index out range
Ответитьi have doubt why they give me the error they say me every :::: index out of range
ОтветитьLove every minute of this video!great tutorial!thank you so much!
ОтветитьThis line keeps throwing errors
fitModel = model.fit(x_train, y_train, epochs=40, batch_size=512, validation_data=(x_val, y_val), verbose=1)
For everyone who as problems installing the pip package, its only for python versions up to 3.8. If you are running python 3.9 or higher install the alpha version of the pip package
ОтветитьSuper clear, easy to follow explanations, THANKS!
ОтветитьHi, thanks for this course, But we want source code
Ответитьcan't trust anything a guy using a windows computer says for this.
Ответитьhow is it shrinking the data to devide by the max value? you get a lot of dezimal numbers...
Ответитьhow did you choose 128 neurons for hidden layers ?
Ответитьwow this tf tutorial actually keras tutorial, kinda misleading =(
Ответитьdont you want to evaluate your fit_model rather than your model?
ОтветитьWe're at shella ka deulim metric abullah equals and bibbidi babbidi is why put them together ? and you've got booty babbdi boo x plus y equals y, x equals zero
Ответитьplt.title("Prediction " + class_names[np.argmax(prediction[i])]), I am getting index Out of range error, can you please help??
Ответитьi accidently create skynet..
ОтветитьValueError: Input arrays should have the same number of samples as target arrays. Found 60000 input samples and 10000 target samples.
I am getting this error.. an someone help me
The white background burns my eye
Ответитьidk why its predicting "tshirt " in all the cases with a accuracy of 0.1018
ОтветитьSo cool to find a video on this subject where the teacher does not have a heavy accent
ОтветитьIs this TensorFlow or Keras?
Ответить(x2 + y2 − 1)3 − x2y3 = 0
ОтветитьNice content and explanation, thanks for the video
ОтветитьBest tensorflow tutorial ive ever seen, thanks for this one!
ОтветитьGreat video. Very informative. I tried to follow along and created a model in google colab. My training and testing sizes are 60,000 and 10,000 respectively. However, when the model is being trained, below where it says Epoch 1/5... it shows a total of 1875, whereas in the video tutorial it shows 60,000. Can someone please explain to me why my model is only taking 1875 images as input instead of 60,000. I have checked my training and testing sizes and they are 60,000 and 10,000 respectively. But later it shows to be 1875
Ответитьclass_names is not working .. it says 'class_names' is not defined...what should I do?
ОтветитьGreat crash course
ОтветитьHe became my favorite by saying he doesn't know what Verbose is.
Ответитьgreat tutorial, btw, what is this text editor?.
Ответитьamazing video thanks!
Ответить