codebasics / deep-learning-keras-tf-tutorial Goto Github PK

In deep-learning-keras-tf-tutorial/42_word2vec_gensim/42_word2vec_gensim.ipynb code-block-3 The reading file name should be changed to "reviews_Cell_Phones_and_Accessories_5.json" instead of "Cell_Phones_and_Accessories_5.json".

df = pd.read_json("reviews_Cell_Phones_and_Accessories_5.json", lines=True)

Thanks!!

If you try to use input_length=4 , it will throw an error saying it is not a valid keyword argument. Although, the same format has been mentioned in tensorflow documentation still it throw this error (Even if I try to reprdoduce the code mentioned in the documentaion).

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int)
Encountered this error for the same. On deep research, I found that it was due to udi8 and bool mis-errors in older(yours) andcurrent version(where tf reads them as bool).
Need to maintain a consistent data type along it. Already created a pull request for it

reviews = [
'Reply to win £100 weekly! Where will the 2006 FIFA World Cup be held? Send STOP to 87239 to end service',
'You are awarded a SiPix Digital Camera! call 09061221061 from landline. Delivery within 28days. T Cs Box177. M221BP. 2yr warranty. 150ppm. 16 . p p£3.99',
'it to 80488. Your 500 free text messages are valid until 31 December 2005.',
'Hey Sam, Are you coming for a cricket game tomorrow',
"Why don't you wait 'til at least wednesday to see if you get your ."
]
model.predict(reviews)
array([[0.6472808 ],
[0.7122627 ],
[0.5710311 ],
[0.06721176],
[0.02479185]], dtype=float32)

can i know what's tag on reviews ?

MemoryError: Unable to allocate 1.99 GiB for an array with shape (2752, 180, 180, 3) and data type float64
.
If the laptop's RAM is less than 8 gb and CPU is not at its full potential then this issue might occur. Recommended:)
Use google collab or just write code for CPU full effeciency so that there are no losses.

for fitting data it must be "x_sm, y_sm = smote.fit_resample(x, y)" and not "x_sm, y_sm = smote.fit_sample(x, y)"

At the last , image height and width aren't been defined due to which it will cause a variable undefined error.

Thank you for this example.
Could you tell me if this is a supervised classification or a non supervised one?
if it is a supervised process, at which step did you match the images with the class name at the learning process step.
Thank you in advance