Me too went into same question but didn't found any answer but yes what you can do is just import model with whatever version you have and if its compatibility issue than you can search err on google you would definitely find right version
i've tried with another image from another dataset and this is the result array([[1.0000000e+00, 7.3135388e-22, 6.7341475e-17, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00]], dtype=float32) the prediction results are very confusing can you explain how this happened ? and how to solve this ?
this is the predictions array you can use np.argmax(predictions) and this will return max index value and from that you can know which index is for which label
X = np.array(X)/255.0 y = np.array(y) /usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray """Entry point for launching an IPython kernel. --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in () ----> 1 X = np.array(X)/255.0 2 y = np.array(y) TypeError: unsupported operand type(s) for /: 'list' and 'float'
@@programming_hut x=no.array(x) x=x/255.0 y = np.array(y) --------------------------------------------------------------------------- NameError Traceback (most recent call last) in () ----> 1 x=no.array(x) 2 x=x/255.0 3 y = np.array(y) NameError: name 'no' is not defined
how i know that the trained on same tensorflow and keras version of production code
Me too went into same question but didn't found any answer
but yes what you can do is just import model with whatever version you have and if its compatibility issue than you can search err on google you would definitely find right version
Why its showing happy emotion for any type of image?
Can you please provide the dataset
can I get the project report
Hi nice and informative video but I followed the tutorial and created my model but my predictions are not correct any Idea what could have been wrong?
Bro do u have numpy array videos
nope, only one video of reshape
i've tried with another image from another dataset
and this is the result
array([[1.0000000e+00, 7.3135388e-22, 6.7341475e-17, 0.0000000e+00,
0.0000000e+00, 0.0000000e+00]], dtype=float32)
the prediction results are very confusing
can you explain how this happened ? and how to solve this ?
this is the predictions array
you can use np.argmax(predictions)
and this will return max index value
and from that you can know which index is for which label
@@programming_hut I tried this np.argmax(test_img)
And got output as 1613
What kind of prediction is this?
Why you passing testimg directly send the model prediction in it
😍😍😍😍😍😍😍😍😍😘😘😘
thanks
@@programming_hut welcome g
X = np.array(X)/255.0
y = np.array(y)
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
"""Entry point for launching an IPython kernel.
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
in ()
----> 1 X = np.array(X)/255.0
2 y = np.array(y)
TypeError: unsupported operand type(s) for /: 'list' and 'float'
Can u solve this error
what's inside X
try this
x=no.array(x)
x=x/255.0
@@programming_hut
x=no.array(x)
x=x/255.0
y = np.array(y)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
in ()
----> 1 x=no.array(x)
2 x=x/255.0
3 y = np.array(y)
NameError: name 'no' is not defined
sorry its "np"
Bro for each image it is predicting happy.
you should imporve your way of explaination
Ok 👍 sure
can I get the project report