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

Hey bro, when will finish the expination of your book ??

Hello :) Do you have published ypur code of the CNN on GitHub?

I have two problems in tensorflow 2:
I fixed the following two problems:
1. y = np.array(y) # this convert the array y into nnumpy arry for model.fit() error.
2. My Video RAM in GPU can be not enough. I turn off GPU mode in Tensorflow 2.
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
then, it runs.

you look like lil peep lol

how to improve the accuracy?, what is the logic if changing filter sizes,adding more layers, more dense layers to improve accuracy

tea cups game strong

I'm doing image clasification for traffic signals which has more than 50000 images, but i keep recieving not enough memory to allocate, 115GIB error, can anyone help?

I followed what you did and for some reason I only train through 702 images, why is that?
Edit: changed batch size to 1 and it worked

I'm a little lost here. How does the engine know how to label an image as a dog or a cat. How does it know to get the labels the right way around? I can't see where you tell the engine. "hey this image is a dog"

I am getting valueError: logits and labels must have the same shape, received ((32, 1) vs (32, 50, 50, 1))

Once u train Ur code for epoch = 5 and i décidé to train it for epochs=10 then will you like restart everything like schufling again thé images and everything then start a brand New epochs=10 or will you juste continue with same order of images and the first epochs 5 u will liké just add 10 now its liké u did 15 epoches

HOW TO MAKE NOW PREDICTION?

Hi can you help me in cnn-traffic-sign-identification.ipynb

very strange mug :)

sentdex when are you gonna update this course ?

Are these results normal? it took 4min (approx.) for each epoch i have intel i7-10th gen cpu
Epoch 1/3
546/546 [==============================] - 229s 418ms/step - loss: 0.6330 - accuracy: 0.6417 - val_loss: 0.5930 - val_accuracy: 0.6887
Epoch 2/3
546/546 [==============================] - 239s 437ms/step - loss: 0.5550 - accuracy: 0.7162 - val_loss: 0.5284 - val_accuracy: 0.7382
Epoch 3/3
546/546 [==============================] - 243s 444ms/step - loss: 0.5080 - accuracy: 0.7515 - val_loss: 0.5797 - val_accuracy: 0.7050
--------------------------------------------------------

my y values = 1,1,1,1....... 🤔 can i get some help please how to index this data properly

Please how can I load a .raw dataset for CNN

Hello, I encounter a problem with this code. When I execute the code, I got the error "could not load dynamic library 'cublas64_11.dll'; dlerror: cublas64_11.dll not found." Therefore, I went to check whether my CUDA files correspond to my Tensorflow. However, I found that the version of CUDA was 11.6, which is not compatible to any current version of Tensorflow now. What should I do to solve this problem? Thank you.

Good day! I just have some inquiries regarding about the error I've got , it says " ValueError: `logits` and `labels` must have the same shape, received ((None, 1) vs (None, 50, 50, 1))", though I have followed all the code and still got this error, thanks.

You are a amazing teacher ❤️

what to do when i get this error

Input 0 of layer "conv2d" is incompatible with the layer: expected min_ndim=4, found ndim=2. Full shape received: (None, 1)

while compiling the model when i use Conv2D the first time

Can anyone help me with CNN code that takes NDVI data as input and gives class label as output !?

Just amazing! You are really helping me with my paper! 🙌

Thank You, Good explanation 👍🔥

Any advice on how to pass the computations from cpu to gpu ( model training) ? I can't find the right combination of tensorflow-gpu, cudnn and cudatoolkit. I tried many things but didn't work and I need some basic guidance , a right mind approach.

How to measure sensitivity and specifity?

Can you please explain the science of wisely choosing the critical/essential arguments in various layers, i.e., how to select the number of filters, kernel_size etc., in a CON2D layer? Similarly, whats the science behind adding layers upon layers? I would be grateful if something could be added other than the usual answer of 'more layers in deep learning help in extracting hidden features/patterns'. Please share a link to your video if you have already done it.
To the broader audience, please share a video that you may have found very informative about choosing the parameters for various layers? And how to transition from layer to layer?

I don't understand my error and why you don't have it. I have got this one : "unsupported operand type(s) for /: 'list' and 'float'" be cause of "X = X/255.0" but I don't found a solution if someone got one. But your tutorial is very good and helpful. Thank you

can you use this method to make Alzheimer's detection using MRI or if possible use Faster RCNN?

hay sentdex, could you give us the pickle data?

Hi, can you explain about the data set you had used?

got error when run model train = `validation_split` is only supported for Tensors or NumPy arrays,
how to fix this?

I have 24946 features and labels, but only 702 is used in model.fit() Can someone help me in this?

Help me a lot! By the way, your cup is soooooooo cute!

helo edward snowden

what will be the architecture of cnn if there are 2 inputs and 1 output ?

InvalidArgumentError: Graph execution error: -->Any Idea of this error, it is coming when I am training VGG16 of keras , I have used ImageDataGenerator

Hi I have a very annoying error: the reshape changed and it just accepts 2 inputs now… How to correct it?

how does your program train so fast? For each epoch I get an ETA of 5 minutes. My computer is a good one so what gives. Is it because you are using jupiter notebook or something else?

Love that mug 🙂

For anyone getting the following error "validation_split is only supported for Tensors or NumPy " add y = np.array(y) under X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE,1)

I am getting following error after running this code:
ERROR! Session/line number was not unique in database. History logging moved to new session 114

Can anyone please help?

Why didn't we use conv1D or conv3D here? Please someone explain this to me that what's the difference between conv1D, conv2D and conv3D?????

FileNotFoundError: [Errno 2] No such file or directory: 'X.pickle'
can anyone answer this:)

Nice hands on explanation of CNN