All Questions
20 questions
1
vote
0
answers
194
views
How to predict the class probability with an array
I have an array of data and I'm trying to predict the probability if it's 1 or 0
I have a data set with more than 3000 rows as features and output data is either 1 or 0.
I'm quite new with neural ...
- 77
0
votes
1
answer
407
views
I'm facing below issue whe I train the model using VGG16
I am facing the following issue, when trying to fit my model:
ValueError: Input 0 of layer "model" is incompatible with the layer: expected shape=(None, 256, 96, 3), found shape=(None, 1, 8, ...
- 241
0
votes
0
answers
1k
views
Why the accuracy and val_accuracy are stuck at 0 LSTM Keras classification
I'm trying to train a neural network for classification. The target labels are -1 or 1.
The neural network is as follows:
def build_nn(window,n_features,lr = 0.001):
_input = Input(shape = (window,...
1
vote
0
answers
87
views
In the classification of three classes, accuracy does not improve by 46% under any circumstances
i have a network for classify data into 3 class.data are 13760 Two-dimensional array with 19 row and 1280 column and data type is float(In fact, my data is eeg). first trained network by convolution ...
3
votes
0
answers
341
views
Loaded Keras model from .h5 file is not predicting correctly like the original one after training
I am new to ML and I am trying to play a little with this tutorial:
https://medium.com/@ferhat00/deep-learning-with-keras-classifying-cats-and-dogs-part-2-21b3b25bbe5c . Anyway, the CNN seems to work ...
- 69
0
votes
0
answers
158
views
Good Accuracy + Low Val_loss but very bad predictions
Going straight to the problem...
I am using Keras flow_from_directory to load the data for sound classification. Data_generator without any augmentation and shuffle =True and although most of my ...
- 1
-1
votes
2
answers
296
views
Neural Network doesn't learn - simple classification problem
I am currently trying to learn simple neural network recognize 4 different outputs. There are 2-value-inputs which are actually something like this:
output + uniform(-0.2,0.2) + 1
There are only 200 ...
- 69
2
votes
1
answer
6k
views
How to find the wrong predictions in Keras?
I have built a Keras model for extracting information from a raw input of text input. I am getting an accuracy of 0.9869. How can I know which of the training data is making the accuracy go low? I ...
0
votes
1
answer
446
views
How to loop when predicting in keras text classification model
I am new to keras. I wrote a text classification model and when making predictions for one input ,I am geting the right predictions as shown below:
text=["Cancelling insurance cover that is in excess ...
- 75
3
votes
1
answer
181
views
ValueError: Error when checking target: expected dense_3 to have shape (1,) but got array with shape (6,)
I'm trying to run a multi class classification using the following ANN model:
classifier = Sequential()
classifier.add(Dense(units = 9, kernel_initializer = 'uniform', activation = 'relu', input_dim ...
- 6,935
0
votes
1
answer
493
views
Keras - steps_per_epoch calculation not matching with the ImageDataGenerator output
I am working on a basic Classification task with Keras and I seem to have stumbled upon a problem where I need some assistance.
I have 200 samples for training and a 100 for validation, I intend to ...
- 1
2
votes
1
answer
3k
views
How to increase the accuracy of the keras model and prevent overfitting
I am trying to train
model.add(Conv2D(32, (3, 3), kernel_initializer='random_uniform', activation='relu', input_shape=(x1, x2, depth)))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
...
- 147
5
votes
1
answer
118k
views
NameError: name 'image' is not defined
I am getting the error in the post title when I attempt to run a pretrained MobileNet classification. The image I am using to run the script is located in my 'MobileNet-inference-images/American_Cam....
- 515
-2
votes
1
answer
674
views
how to reshape a dataset for RNN/LSTM model? [duplicate]
I am trying to build an RNN/LSTM model for binary classification 0 or 1
a sample of my dataset (patient number, time in mill/sec., normalization of X Y and Z, kurtosis, skewness, pitch, roll and yaw, ...
- 291
0
votes
0
answers
43
views
How to insert word on specific position in vector Keras
How to insert word on specific position in vector using Keras and pad_sequence?
For example I have sentence:
1) XYZ1 is a specific word
2) Specific word is a XYZ1
Above we have 5 unique tokens:
...
- 31