Convolutional Neural Networks - Deep Learning basics with Python, TensorFlow and Keras p.3 

Happy to share!

dont know why he didn't do that

Thanks for this solution, I was stuck.

after doing what you suggested I got this error File "", line 3, in raise_from tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[194] = 194 is not in [0, 194) [Op:GatherV2] ps: 194 is the size of my dataset

Thanks

Thanks, It worked! I was getting some weird Tensorflow InvalidArgument errors and I was stuck..

thanks a lot, that solved it for me too

Thanks worked like charm!

thank u very much

thank you!

thank you

Thanks

looking forward to your transfer learning videos

Agreed ! Please do one. Badly waiting for that

Why not use dense layer with 2 nodes in the end, why one ? please help in explaining

@@curious_one1156 Because one node can be both on and off ,1 and 0, cat and dog

@@sklify1232 So what if you put your output layer as "2". Then would you technically have 3 output classes? Ex. "Cat", "Dog", and "Airplane"?

@@michaelschmidlin4274 I think it would still be cat and dog, so it's an equivalent alternative to one node for binary choice. You could say "airplane" when both of the 2 nodes are off , but it would depend on the activation threshold- too cumbersome.

was gonna say the same thing lol

I wanna buy one

@@sungyoungkim4382 where to get the coffee cups

Can you tell me the steps to install tensorflow-gpu and my epoch is running very slowly @MRH

@@rizwanrehman6833 use google collab instead

I know the feeling

Hello Dear I am facing following error. I am using same syntax as you did.... FileNotFoundError Traceback (most recent call last) in ----> 1 X = pickle.load(open("x.pickle","rb")) 2 y = pickle.load(open("y.pickle","rb")) 3 X = X/255.0

can you elaborate more where do you put that code?

No more wait! ...til the next video :)

you're awesome man :D

Whoops. yep, that's a mistake lol.

for some reason i got better accuracy in the same amount of epochs when i didn't add an activation function for that layer

King Neptune whatever that reason might be but a layer without an activation makes no sense

Brother Lui yeah I agree it'd be useless

There has been some study of "all Conv" models where only the output layer is fully connected, generally results in greater accuracy.

In tutorial #2 Harrison converted X to a numpy array, and it's possible that definition is still hanging around here. Before the division, add the following lines and you should be good to go: import numpy as np X = np.array(X)

@@markd5928 I know it's been three years for you lol, but THANK YOU for this. I was pulling my hair trying to figure this error out.

usually you implement a dropout if your model has overtrained. So you randomly "drop out" certain connections in hopes to make your model more generalizable. Of course, it will probably also reduce accuracy for validation purposes.

bless you

Thank you Ramzy.. Your solution solve my problem..

I dont know if you still need this but what I did was: Image_size = (your image size) CatDogModel = tf.keras.models.load_model('(put the name of your model save file here)') ImagePath = "(Path to your image)" Image = cv2.imread(ImagePath, cv2.IMREAD_GRAYSCALE) NewImage = cv2.resize(Image, (Image_size, Image_size)) NewImage = np.array(NewImage).reshape(-1, Image_size, Image_size, 1) prediction = CatDogModel.predict([NewImage]) a = prediction[0] print(a) 0 is dog and 1 is cat. (I did all of this in a separate python script.) I dont know if I did it in the best way but that's what I did.

import numpy again and reconvert to nparrays after loading X = np.array(X) y = np.array(y)

savior

yes, the solution lies within the 2nd video, a slight edit should be made in 2nd video in order for the 3rd video code to run. In the section wher the x has been made into an array, y should also be made into an array. The line goes something like this : X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1) y=np.array(y) This would solve the value error problem, as they both are fitted into two individual arrays.

same problem, any fix?

That means that your reshaping didn't go well, you could try to check the image size you constructed the data with and run it again

X.shape[ 1 ] returns an int e.g. 7 X.shape[ 1 : ] returns a tuple e.g. (7, ) so the colon would return a tuple instead of an integer, not sure if that helps?

Hamish Okay, thanks!

Actually its for slicing. X.shape[1:] means he is getting the tuple X.shape, but without the first element. Example: X.shape returns (a, b, c, d) X.shape[1:] returns (b, c, d)

The problem is that X is a numpy array and y is just a list. What I did is: X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1) y = np.array(y)

@@vaizerdgrey thanks this worked!

@@@vaizerdgrey it worked thanks buddy

thanks! helped a lot

How to install tensorflow-gpu ?

@@rizwanrehman6833 www.tensorflow.org/install/pip this should help :D

@@paulroberto2286 No mac support sadly :-(

10 epochs :o ?

USE gpu of ur computer, perhaps u have figured that out already

I am getting the same error.

Solved the problem: The problem is that X is a numpy array and y is just a list. put from numpy import array in the import statements and change the y assignment to y = array(pickle.load(open("Y.pickle","rb")))

@@rubenuribe love u

@@rubenuribe gracies maquina

@@rubenuribe Freaking love you man !

try creating a new variable that stores a resized X with an additional dummy dimension, something like "resizedX = numpy.resize(X, (1,X.shape))" and put that resized X into your fit function instead of the normal X

@@x3epic763 What Do you mean? Could you explain more? I'm getting the same error, but I don't know what you're saying

@@jordenquast2655 well the error kinda says that the function expected a 4 dimensional input but received a 3 dimensional one. Therefore you can try adding a 4th "dummy" dimension as the first dimension to the input. So say your input has the shape (200,5,5) then the new input should be (1,200,5,5).This can be done with the resize function: you make a new variable and store the result of the function as the input. This new variable can then be used as input for the training function. It depends on the overall setup if this will work, but ive seen the problem solved like this a couple of times

@@x3epic763 I solved it, there error was in the last line of the data transformation code, where it took some dimensions away. This left it with too few dimensions to be able to run. I believe the line of code was X = np.array(X).reshape(-1, imgSize). Hope this helps someone!

@@jordenquast2655 specifically this is the correct line: X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)

it's most likely a server

he has a high-end gpu. if you're on a budget I picked up a 1060 6gb on ebay for like $130 and it trains models really fast for the $$

@@waynefilkins8394 yes but i think he uses paperspace and does his development on their servers.

what is your link?

Your model is overfitted