Stack Overflow
Stack Overflow

Questions tagged [loss]

599 questions
0
votes
1 answer

random byte loss when streaming data over network

My issue is that when i'm streaming a continuous stream of data over a LOCAL LAN network sometimes random bytes gets lost in the process. As it is right now the code is set up to stream about 1027 bytes or so ~40 times a second over a lan and…
bbuubbi
  • 3
  • 2
0
votes
0 answers

Data loss in UDP socket due to different connection speed between Client and server i

I m working on a project for sending some big size object throw UDP protocol (written in C#), all works well. The problem is that there is a difference in connection speed between the Client and Server that causing a loss of about 70 % of the…
user2492258
  • 11
  • 1
  • 3
0
votes
1 answer

C++ SFML Sprite Losing Data

I have two classes in my WIP Tetris clone, and one is instantly called by the main function. The .h and .cpp files for this class are here: http://pastebin.com/mDMeqMfV The second class which the first class has an instance of, can be found here:…
Oracular
  • 367
  • 1
  • 4
  • 13
0
votes
1 answer

JPA merge: Not sure what of these two methods below is better. Am getting data loss

I'm not sure if I should be setting the object to the result of the merge and then return that, or just do a merge. I'm using the technique in the first block below but I am sometimes losing data and I don't know why. @Override public T save(T…
Novarse
  • 51
  • 1
  • 10
0
votes
1 answer

C#, Win CE 4.2, Write file, power loss

I'm using C# & the compact framework on an embedded device to log data to a compact flash card. Because data integrity is of upper most importance, I'm wondering how to write the data to the flash disk. Will files get lost/damaged if power is lost…
Korexio
0
votes
1 answer

When logging into Facebook through application the page refreshes

The first page of the application passes a value over to the next page using a text box. If the user isn't logged in then it will display a login link that will allow them to do so. Whenever they click the link the page will refresh which drops the…
Gary Odums
  • 3
  • 1
-1
votes
1 answer

Why Are Floating Point Numbers Inaccurate in IEEE754?

As we know, data type float in C comply with IEEE754. And float has 24 significant binary digits. Therefore, if it exceeds 24 bits, accuracy loss will occur. In that way, how many decimal digits can float represent at most without loss of accuracy?…
zhenyoung
  • 21
  • 3
-1
votes
2 answers

Curious loss in a CNN

in my CNN for image classification, I get a curious loss and I don't know what's wrong. I'm lucky, if you help me to find the failure. Here is a cutout of my print output and at the end there is my code: Train Epoch: 1 [0/2048 (0%)] Loss:…
Christian01
  • 307
  • 1
  • 5
  • 19
-1
votes
1 answer

Linear Regression with Pytorch : constant loss

I'm working on a linear regression problem with Pytorch (y=A*x, where the dimensions of A are 2x2). I wrote the following code. I don't know why the loss doesn't change... Can someone help me ? Thanks, Thomas import torch import numpy as np from…
spe2005
  • 3
  • 1
-1
votes
1 answer

What is possible error on communication with TCP, UDP, serial?

I'm developing app containing TCP, UDP, serial connections. I heard that there are some errors or losses in communication. However, I don't know exactly what kind of errors should be handled. What kind of errors are possible for each method? change…
Gimun Eom
  • 411
  • 5
  • 17
-1
votes
1 answer

How to implement getting loss with pytorch on NLP?

I'm studying about NLP with just simple toy project(just gernerating text) with pytorch. While i'm referencing some example code on online, got a problem i can't understand. Here are codes (some codes has been omitted and are not completed…
GE LO
  • 107
  • 1
  • 4
-1
votes
1 answer

Binary Crossentropy accuracy of keras model is not changing

I have seen many questions of this problem online, but there are no definitive solutions and my case might be different, as it is with time series data and a LSTM architecture. model = Sequential() model.add(LSTM(50, activation='relu',…
Victor Sim
  • 358
  • 1
  • 13
-1
votes
1 answer

how can I sum float number with loss list ? I receive error

I used loss_val.item() instead of loss_val.data[0] in my code because new version of python do not support that but as you can see here but I receive Error for gathering Loss in list " 'float' object is not iterable" do you know what should I do…
ELI
  • 45
  • 7
-1
votes
1 answer

Training accuracy doesn't increase of PointNet Tensorflow 2.0 Implementation for ModelNet40 Dataset

I re-implement pointnet using tensorflow 2.0, and I try to train the model using modelnet40 datase for classification. The training loss will decrease along with apochs increase, but the accuracy dosen't change, no matter I use data augmentation or…
Yongsheng
  • 1
  • 1
-1
votes
1 answer

Noisy train loss after specific epoch in LSTM for time series forecasting (Keras)

I'm training LSTM model for time series forecasting. This is the train loss plot. This is a one-step-ahead forecasting case, so I'm training the model using a rolling window. Here, we have 26 steps of forecasting (for every step, I train the model…
Eghbal
  • 3,892
  • 13
  • 51
  • 112
1 2 3
…
39
40