Hi, We are using 32 x 32 image size for faster training but you can use larger image size to bring the model accuracy past 80%. You can also try other tuning parameters to improve accuracy. Please comment below your accuracy.
Once you trained the model at the end of the video, how do you select an image and a label and test the model with them to see if the model predicts well the animal?
Opps. Thanks for pointing it out. That is a huge mistake. Sequential layer should be used only once before we start adding the layers. Thanks for suggestions.
@@KGPTalkie Sir I was following your series! Special thanks for the efforts, While following this video I was facing this error ValueError: Shape mismatch: The shape of labels (received (60,)) should equal the shape of logits except for the last dimension (received (20, 3)). Can you help me resolving this
hey do you help me? when ı use ImageDataGenerator(rescale=1./255) accuracy drops, normaly accuracy is very high when i'm using images range[0,255]. Why?
I maybe late here but your github link is not working .. And since you have structured your data properly like train>dogs has dogs images and cats have cats images ! my dataset which is the same I downloaded from kaggle has all the images together so while image data gen It gives 37000+ images and you had 20000 images
Thanks for watching. Yes that happened because I copied first three lines and forgot to delete first line during past. The github code is upto date. You can download and run it. It should work.
The variable "valid_data_dir" wasnt declared. Where should it point to? NameError Traceback (most recent call last) in () ----> 1 validation_generator = datagen.flow_from_directory(directory=valid_data_dir, 2 target_size = (32, 32), 3 classes = ['dogs', 'cats'], 4 class_mode = 'binary', 5 batch_size = batch_size) NameError: name 'valid_data_dir' is not defined
Hi, It happened because jupyter notebook stores variables in cache and for some other project I had declared valid data dir and by mistake I used in this. You got it right, it should be test data dir
@@KGPTalkie Please make a live project series from Web Data scrapping to Feature engineering- Model Selection-Evaluation-Deployment. It can help us get a good depth of how Actual Data Science and actual ML project works in an Industry and help us get industry insights
38:18 You must REMOVE model = Sequential() from lines 5 and 9 `model already defined in 1 if you print your model you will check the architecture !
Hi, We are using 32 x 32 image size for faster training but you can use larger image size to bring the model accuracy past 80%. You can also try other tuning parameters to improve accuracy. Please comment below your accuracy.
Sir I think you are busy in some matter. But we are anxiously waiting for your videos
Thanks for encouragement. I am on leave. Will start LSTM next week.
Once you trained the model at the end of the video, how do you select an image and a label and test the model with them to see if the model predicts well the animal?
HI! I have question : Why we have to change this image to array form and not in minst fashion dataset. Help me out
Hi KGP, I'm wondering why you use the test-set for the validation and not a true validation-set? Thanks! Great work
Test set was unseen so it can be used
sir please make video on training on own dataset of like 4 or 5 different types and also show the prediction on live camera feed
Yeah sure. Please keep watching.
why are you initializing the object of sequential several times??
Opps. Thanks for pointing it out. That is a huge mistake. Sequential layer should be used only once before we start adding the layers. Thanks for suggestions.
I was also wondering about the same issue!
It was a mistake. I did copy and paste.
@@KGPTalkie Sir I was following your series! Special thanks for the efforts, While following this video I was facing this error ValueError: Shape mismatch: The shape of labels (received (60,)) should equal the shape of logits except for the last dimension (received (20, 3)). Can you help me resolving this
you need to reshape your data
if i use dataset of diabetic retinopathy and train it using VGG 16 model does it work??
Yes. It should work but before that please watch my videos on VGG16 network.
Again Model.fit_generator is deprecated starting from tensrflow 2.1.0...☠️🙄 and i am using 2.6.0
It's giving me error...cannot identify image file
Thanks for watching. You can now Download Dog Cat Dataset by this link. github.com/laxmimerit/dog-cat-full-dataset
hey do you help me? when ı use ImageDataGenerator(rescale=1./255) accuracy drops, normaly accuracy is very high when i'm using images range[0,255]. Why?
Rescale is required only when pixel values are in between 0 to 255. Please check in your original data what is range of pixels.
please sir make video on LSTM, RNN etc
Yeah sure... From next week onwards, I will start with LSTM.
I maybe late here but your github link is not working .. And since you have structured your data properly like train>dogs has dogs images and cats have cats images ! my dataset which is the same I downloaded from kaggle has all the images together so while image data gen It gives 37000+ images and you had 20000 images
Btw Thanks u make awesome videos also u explain in a very great manner
Thanks for watching. You can now Download Dog Cat Dataset by this link. github.com/laxmimerit/dog-cat-full-dataset
@@KGPTalkie Thankyouu 💯..
good job but u have a single mistake in cell 23.
you should remove lines 7 and 13 'model=Sequential()'
I don't know how is it run with u
Thanks for watching. Yes that happened because I copied first three lines and forgot to delete first line during past. The github code is upto date. You can download and run it. It should work.
The variable "valid_data_dir" wasnt declared. Where should it point to?
NameError Traceback (most recent call last)
in ()
----> 1 validation_generator = datagen.flow_from_directory(directory=valid_data_dir,
2 target_size = (32, 32),
3 classes = ['dogs', 'cats'],
4 class_mode = 'binary',
5 batch_size = batch_size)
NameError: name 'valid_data_dir' is not defined
I believe the correct variable is "test_data_dir"
@@jfabian yeah i think so too, but why in the video he can use valid_data_dir without problem? i didnt see any initialization with that name before
@@GilangD21 I'm sure he declared it before (not shown in the video)
Hi,
It happened because jupyter notebook stores variables in cache and for some other project I had declared valid data dir and by mistake I used in this. You got it right, it should be test data dir
@@KGPTalkie good. Great work. Love your videos
valid_data_dir not declared??
Please change that to test_data_dir Thanks for watching.
The new corrected file is reuploaded. Please check and let me know if it is not working.
why is it 64, 128, 256 number of filters?
You can use any number of filters.
@@KGPTalkie How do we know which number to put?
Can you prescribe a good book on Deep Learning? Thanks
@@KGPTalkie Please make a live project series from Web Data scrapping to Feature engineering- Model Selection-Evaluation-Deployment. It can help us get a good depth of how Actual Data Science and actual ML project works in an Industry and help us get industry insights
very low voice,