365体育足球滚球比分

Questions tagged [machine-learning]

365体育足球滚球比分 Implementation questions about machine learning algorithms. General questions about machine learning should be posted to their specific communities.

Filter by
Sorted by
Tagged with
0
votes
0answers
3 views

Why Is My Machine Learning Algorithm Getting Stuck?

So I am hitting a wall with my Machine Learning project. I am attempting to train an algorithm to recognize numbers. Since this is only an exercise I have a image set of 200 numbers (20 each for 0 ...
0
votes
0answers
5 views

Python model for correcting the input data

I need to build a model by taking historic data of a list of fixed length having text of fixed values for each index. Example: [ABC,BCD,CDE,DEF,EFG] The model should correct the input new list if ...
0
votes
1answer
6 views

Train Mask R-CNN on custom dataset

I hope you are doing well; I am new in deep learning but also with mask r-cnn, I have some confusion, mask r-cnn with the original trained model can recognize persons, I try to train mask r-cnn with ...
1
vote
0answers
13 views

(ε, δ)-differential privacy accuracy/privacy trade-off

I'm using Renyi (ε, δ)-differential privacy as implemented in PyTorch DNNs. I do this to guarantee the privacy of the training set to the degree ε. In order to implement this, I use PyTorch-DP. As the ...
0
votes
0answers
8 views

Training error in history is not defined using MNIST data set

I am new to deep learning...I am getting problem like this ,i am training model to recognize hand written digits ..i used MNIST data set import tensorflow as tf def train_mnist(): class ...
0
votes
0answers
8 views

Handling imbalanced data error and attribute not found

I use Spark, PySpark and Anaconda Jupyter Notebook to run the code. I get syntax error on this line train=train.withColumn("classWeights", when(train.class==0,BalancingRatio).otherwise(1-...
-1
votes
0answers
16 views

What should I use python or c++ with firebase for making my program to work fast? [closed]

Should I go with python or c++ with firebase for making my program to run faster. I tried python + AWS but there was a 7-10sec delay for my program to run. Suggest me a better answer
1
vote
0answers
11 views

How to train your own(w/o YOLO etc.) object detector in tf/keras

I successfully trained multi-classificator model, that was really easy with simple class related folder structure and keras.preprocessing.image.ImageDataGenerator with flow_from_directory (no one-hot ...
0
votes
0answers
5 views

Is there any pre-fitted Keras tokenizer?

In Text data preprocessing in keras, we use Tokenizer class. But if we fit the training data in the Tokenizer, then any new word in the testing set does not get identified when generating sequences. ...
0
votes
0answers
8 views

What can we do about a project based on IoT, Machine Learning and Python? Details in description

To create an architecture for IoT devices such that: N IoT devices(Remote nodes with sensors) read sensor data and publish it using MQTT client, M IoT devices(Training nodes) receive that data by ...
0
votes
0answers
2 views

eError: Could not build a TypeSpec for && ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray)

There is a question similar to the above one but there is no "exact answer for that question", so i request you not to delete the question. -> I got this error while trying to fit my image classifier ...
0
votes
0answers
8 views

machine learning framework for irregular RPC traffic detection by predicting future traffic [closed]

I'm supposed to Build a machine learning framework for irregular RPC traffic detection by predicting future traffic using Tensorflow. In my framework I supposed to use graph convolution network. I ...
0
votes
0answers
18 views

Discrepancy in the results of model.evaluate and model.predict in Keras

I'm performing multi-class classification with three class labels in Keras. During training, both the training and validation losses were decreasing and accuracies were increasing. After training, I ...
0
votes
0answers
13 views

KFold Cross Validation multiclass recognition in Keras

I‘m trying to do KFold Cross Validation with a multiclass recognition problem. The dataset is the Uc-merced dataset, it contains 21 classes, for each class we have 100 images. This is the code: # ...
-1
votes
0answers
7 views

Current state of quantum-enhanced machine learning techniques

Hearing a lot about Quantum Machine Learning, I'm curious how many of the proposed quantum machine learning algorithms serve an advantage (speed or accuracy) over their classical counterparts. And if ...

15 30 50 per page
1
2 3 4 5
2684