Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with deep-learning
Search options not deleted
user 45264
a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.
0
votes
Is the output size of the last layer of a standard fully connected neural network the same a...
No - the input and outputs sizes are independent from one another in a deep full-connected network. You could e.g. have input matrix shape (100, 100, 100) and output shape (1,).
- 15.1k
2
votes
What is "$D$ equal to $\frac{1}{2}$ everywhere" in original GAN paper
$\mathbf{D}$ is the Discriminator network, but it really is being modelled as a probability distribution - the discriminator:
estimates the probability that a sample came from the training data ra …
- 15.1k
2
votes
Accepted
Tuning the model parameters vs the parameter of optimizer for Deep Neural Networks?
The short answer, is that you want the fastest way to reach the performance you expect/desire. This would mean first playing with some hyperparameters like learning rate, initialisation strategy, tryi …
- 15.1k
0
votes
Accepted
Making predictions from keras with SciKit
This seems about right.
You can use SciKit learn quite easily, as the predictions and test results you have should all be in NumPy arrays anyway. Take a look at the regression metrics. The metrics yo …
- 15.1k
0
votes
Accepted
Mini batch size and reset states
You can simply make your training data a shape that is divisible by 50.
In [1]: sample_size = 63648
In [2]: to_remove = sample_size % 50
In [3]: end_index = sample_size - to_remove
In [4]: mode …
- 15.1k
0
votes
Do you apply confidence threshold before calculating mAP for YOLOv2?
I would try both and see how big the difference is. It will depend on how clusttered your images are and how you otherwise threshold the mAP score. Will you for example ignore any bounding boxes that …
- 15.1k
2
votes
Accepted
training when Multiple labels per image
Assuming you want to classify the images (and not use bounding boxes to locate classes within each image), a common way it to create a target vector for each image, which holds the information regardi …
- 15.1k
2
votes
inputs and outputs of a fully connected layer for a note classifier
Starting with your last question: The final fully-connected layer shoud output the number of target classes you have. This output can then be passed to a softmax, which normalises the values between t …
- 15.1k
0
votes
CUDA_ERROR_OUT_OF_MEMORY: out of memory. How to increase batch size?
It could be the case that your GPU cannot manage the full model (Mask RCNN) with batch sizes like 8 or 16.
I would suggest trying with batch size 1 to see if the model can run, then slowly increase t …
- 15.1k
0
votes
Best way to deploy and Schedule Deep Learning Model
other than using a cronjob because it will be unnecessary to pay for the time and resources when it will not be in use
It sounds like you want to use cloud compute.
I would suggest looking at th …
- 15.1k
2
votes
Recreating ResNet50
I am afraid it is not that simple - Have a look at this pretty good walkthrough.
The table you posted is a kind of overview that doesn't contain all the details of how the "blocks" are linked. Other …
- 15.1k
7
votes
Accepted
The Bias-Variance Trade-Off
One way to look at this is through the idea of under-/overfitting
First off, here is a sketch of the generally observed relationship between bias and variance, in the context of model size/comlpexity …
- 15.1k
10
votes
Accepted
Is a large number of epochs good or bad idea in CNN
If your model is still improving (according to the validation loss), then more epochs are better. You can confirm this by using a hold-out test set to compare model checkpoints e.g. at epoch 100, 200, …
- 15.1k
77
votes
Accepted
What does Logits in machine learning mean?
Logits interpreted to be the unnormalised (or not-yet normalised) predictions (or outputs) of a model. These can give results, but we don't normally stop with logits, because interpreting their raw va …
- 15.1k
2
votes
Can we change the structure of the feature-extraction layers of deep networks architectures?
You can change whatever you like!
The benefits will depend on your data and what exactly you are comparing to. As you didn't say exactly what sequence you have as your starting point, I can't compare …
- 15.1k