All Questions
16 questions
0
votes
2
answers
78
views
why the output of filtering pandas file becomes NaN?
I want the output becomes non NaN value.
the problem in this line
f_bp_max.loc[l, 'max'] = df_frcst[df_frcst['Datetime'].dt.year == k]['Forecast'].max()
When I print this:
df_frcst[df_frcst['Datetime'...
- 11
0
votes
1
answer
540
views
loss value and val_loss value not decreasing in RNN algorithm for continuous data prediction
I am building a model for house price prediction using RNN and below is the code. The dataset has no null values and is completely cleaned, still I am getting constant and high loss and val_loss ...
- 3
0
votes
1
answer
80
views
How to implement asymmetric relationship in machine learning Classification algorithm?
I am trying to build a classification system, that takes pairs of images as input and output {0 or 1} if image B is sub-category of image A.
Below are some examples of the data.
Input: Image A [Apple ...
- 11
-1
votes
1
answer
83
views
Is there a list about the supported ML-Algorithms in TensorFlow?
I am writing my bachelor thesis on "Machine Learning in Java" and compare frameworks and libraries. Currently I am collecting information about the different machine learning algorithms supported by ...
- 1
1
vote
0
answers
465
views
Why does Keras (tf) Binary Classification predict() always gives extreme probabilities, either zero or one?
I'm trying implement a NN model (wide and deep learning) with tf.keras v2.0 to do some binary classification. I have ~50k training samples and ~10k testing samples. The class distribution is fairly ...
- 61
1
vote
0
answers
221
views
nesterov momentum gradient calculation at predicted point
In nesterov momentum, the Gradient of the error function with respect to the parameters is calculated at a point different from that where the cost was calculated - that is, the model jumps ahead a ...
- 195
1
vote
1
answer
539
views
Simple classification in TensorFlow
I have the following problem:
I have a raspberry pi robot which uses four sensors (left, front, right, back).
The robot can do the following moves: Run forward, turn left, turn right, move back.
...
- 1,729
29
votes
7
answers
2k
views
Is there a better way to guess possible unknown variables without brute force than I am doing? Machine learning? [duplicate]
I have a game with the following rules:
A user is given fruit prices and has a chance to buy or sell items in their fruit basket every turn.
The user cannot make more than a 10% total change in ...
- 26.1k
-1
votes
1
answer
1k
views
Finish Tensorflow training in progress
Data loss: not an sstable (bad magic number): perhaps your file is in
a different file format and you need to use a different restore
operator?
I'm currently training Tensorflow-wavenet with a ...
- 7,561
-3
votes
1
answer
92
views
What machine learning algorithm to use for face matching? [closed]
I want your opinion on what would be the best machine learning algorithm, or even better, library, to use if I wanted to match two faces that look similar. Kind of like how google photos can put ...
0
votes
1
answer
130
views
Tensorflow next word predictor bug
I have the following code
flags = tf.flags
logging = tf.logging
flags.DEFINE_string('model', 'small',
'A type of model. Possible options are: small, medium, large.'
...
- 21
6
votes
2
answers
3k
views
Where does machine learning algorithme store the result?
I think this is kind of "blasphemy" for someone who comes from the AI world, but since I come from the world where we program and get a result, and there is the concept of storing something un memory, ...
- 7,569
0
votes
1
answer
644
views
Tensorflow Model for Image similarity detection
I have just started playing with tensor-flow .I am searching algorithm or code in tensor-flow or any other that can help me regarding following problem.
There are 10,000 images in my folder and i want ...
10
votes
1
answer
4k
views
Are there any examples of anomaly detection algorithms implemented with TensorFlow?
I'm fairly new to this subject and I am working on a project that deals with detecting anomalies in time-series data. I want to use TensorFlow so that I could potentially deploy the model onto a ...
- 1,298
6
votes
1
answer
5k
views
TensorFlow: Does it only have SGD algorithms? or does it also have others like LBFGS
Question about TensorFlow:
I was looking at the video and model on the site, and it appeared to only have SGD as an algorithm for machine learning. I was wondering if other algorithms are also ...
- 115