Questions tagged [loss]
599 questions
80
votes
9 answers
Lost code lines when Notepad++ crashed
I was working on a .js file this morning on Notepad++, as usual, when the program just crashed. So I ended it, and re-opened it to see that all my code lines in my .js file, had disappeared, and now all I have left is the file with a size of 0kb…
Netero_sama
- 823
- 1
- 6
- 7
64
votes
4 answers
Cross Entropy in PyTorch
Cross entropy formula:
But why does the following give loss = 0.7437 instead of loss = 0 (since 1*log(1) = 0)?
import torch
import torch.nn as nn
from torch.autograd import Variable
output = Variable(torch.FloatTensor([0,0,0,1])).view(1,…
MBT
- 21,733
- 19
- 84
- 102
41
votes
5 answers
How to interpret increase in both loss and accuracy
I have run deep learning models(CNN's) using tensorflow. Many times during the epoch, i have observed that both loss and accuracy have increased, or both have decreased. My understanding was that both are always inversely related. What could be…
Nitin
- 2,572
- 5
- 21
- 28
29
votes
3 answers
How to train the network only on one output when there are multiple outputs?
I am using a multiple output model in Keras
model1 = Model(input=x, output=[y2, y3])
model1.compile((optimizer='sgd', loss=cutom_loss_function)
my custom_loss function is
def custom_loss(y_true, y_pred):
y2_pred = y_pred[0]
y2_true =…
shaaa
- 503
- 1
- 4
- 16
25
votes
5 answers
ffmpeg convert without loss quality
I need convert all videos to my video player (in website) when file type is other than flv/mp4/webm.
When I use: ffmpeg -i filename.mkv -sameq -ar 22050 filename.mp4 :
[h264 @ 0x645ee0] error while decoding MB 22 1, bytestream (8786)
My point is,…
Jensej
- 1,255
- 6
- 21
- 33
24
votes
1 answer
log loss output is greater than 1
I prepared several models for binary classification of documents in the fraud field. I calculated the log loss for all models. I thought it was essentially measuring the confidence of the predictions and that log loss should be in the range of…
OAK
- 2,994
- 9
- 36
- 49
20
votes
1 answer
Change loss function dynamically during training in Keras, without recompiling other model properties like optimizer
Is it possible to set model.loss in a callback without re-compiling model.compile(...) after (since then the optimizer states are reset), and just recompiling model.loss, like for example:
class NewCallback(Callback):
def __init__(self):
…
Horse
- 361
- 2
- 6
20
votes
1 answer
Loss & accuracy - Are these reasonable learning curves?
I am learning neural networks and I built a simple one in Keras for the iris dataset classification from the UCI machine learning repository. I used a one hidden layer network with a 8 hidden nodes. Adam optimizer is used with a learning rate of…
Ananda
- 2,925
- 5
- 22
- 45
20
votes
3 answers
What is a loss function in simple words?
Can anyone please explain in simple words and possibly with some examples what is a loss function in the field of machine learning/neural networks?
This came out while I was following a Tensorflow…
Federico
- 333
- 1
- 4
- 19
14
votes
1 answer
What exactly are the losses in Matterport Mask-R-CNN?
I use Mask-R-CNN to train my data with it. When i use TensorBoard to see the result, i have the loss, mrcnn_bbox_loss, mrcnn_class_loss, mrcnn_mask_loss, rpn_bbox_loss, rpn_class_loss and all the same 6 loss for the validation: val_loss,…
Mob
- 409
- 1
- 5
- 14
13
votes
3 answers
Noisy training loss
I am training encoder-decoder attention-based model, with batch size 8. I don't suspect too much noise in the dataset, however the examples come from a few different distributions.
I can see a lot of noise in the train loss curve. After averaging…
DavidS1992
- 823
- 1
- 8
- 19
12
votes
2 answers
How to use the BCELoss in PyTorch?
I want to write a simple autoencoder in PyTorch and use BCELoss, however, I get NaN out, since it expects the targets to be between 0 and 1. Could someone post a simple use case of BCELoss?
Qubix
- 4,161
- 7
- 36
- 73
12
votes
3 answers
Why is the logloss negative?
I just applied the log loss in sklearn for logistic regression: http://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html
My code looks something like this:
def perform_cv(clf, X, Y, scoring):
kf = KFold(X.shape[0],…
toom
- 12,864
- 27
- 89
- 128
11
votes
3 answers
Average UDP packet loss and packet re-ordering
I'd like to garner fellow SO'ers experience with regards to the issue of UDP packet loss (or drop-out).
Initially my understanding is that given direct point to point connections where the NICs are connected via a crossover cable and ample buffer on…
Sami Kenjat
- 185
- 2
- 12
10
votes
1 answer
Comparing AUC, log loss and accuracy scores between models
I have the following evaluation metrics on the test set, after running 6 models for a binary classification problem:
accuracy logloss AUC
1 19% 0.45 0.54
2 67% 0.62 0.67
3 66% 0.63 0.68
4 67% 0.62 0.66
5 63%…
quant
- 4,062
- 5
- 29
- 70