A message from our CEO about the future of Stack Overflow and Stack Exchange. Read now.

# Tag Info

## New answers tagged convolutional-neural-networks

0

The Raspberry Pi ZeroW with V2 camera doesn't quite have the specs you need, but it is close: https://picamera.readthedocs.io/en/latest/fov.html#sensor-modes Here's a waterproof enclosure for it: https://www.youtube.com/watch?v=5CWksss_5lQ

1

CNN is used since, it is effectively an optimized use case for dealing with image data. CNN effectively automatically extracts features from an images. Other techniques are more likely to not take full advantage of the data. CNN is able to make full use of the data by also including information from adjacent pixels and downsample through layers. Paper ...

2

In most modern neural network frameworks, the update rules for training can be selectively applied to some parameters and not others. How to do that is dependent on the framework. Some will have the concept of "freezing" a layer, preventing parameters in it being updated. Keras does this for example. Others will do the opposite and expect you to provide a ...

0

Without experimental evidence to back me up, I can not answer this with 100% confidence. However, I am fairly certain that this will cause issues depending on the model. U-net is essentially an auto-encoder, and due to the fact that it is all just one big neural network, it is likely it will learn the easiest pattern (as all NN do), and that is to find one ...

2

The paper you are citing is the paper that introduced the cascaded convolution neural network. In fact, in this paper, the authors say To realize 3DDFA, we propose to combine two achievements in recent years, namely, Cascaded Regression and the Convolutional Neural Network (CNN). This combination requires the introduction of a new input feature which ...

0

@Clement Hui Thanks for your answer, I ask AlexeyAB from Darknet the same question and he add now flag for Darknet for this type of model speed measurments: https://github.com/AlexeyAB/darknet/issues/4627 I added -benchmark flag for detector demo, now you can use command 2652263 ./darknet detector demo obj.data yolo.cfg yolo.weights test.mp4 -...

2

In short: It is easy to quantify information, but it is not easy to quantify its usefulness I'm not sure how exactly you are looking to formalise your experiment, but it might be helpful to consider these points: There is no such thing as an absolute measure of information. The amount of information contained in some dataset is dependent on the underlying ...

2

Simply said, there is no specific "meaning" to the features generated. They are simply features that are fitted through math and calculus, and nobody knows what they represent exactly, and will never knows. However we can run PCA (Principal Component Analysis) to see which feature is the most "important" of all, aka which feature affects the most in the ...

1

You can use the dataset test set as "frames" of video. Test the images with your model and calculate the images per second of the result and that is the same as frames per second. However you should set the batch size to 1 as in the real world scenario. You should also display each image with teh corresponding boxes after inference and remove the accuracy ...

0

Let $n=C*K_w*K_h$. Then you should only need $n$ filters. Not $2^n$ to keep all the information. If you just used the rows of the identity matrix as your filters than your convolution would just be making an exact copy so it definitely wouldn't be throwing away information. On the other hand, there will be a max pooling operation. To simplify the question ...

4

You can use tf.reshape() method (tensorflow doc) to reshape (2048) dimensional tensor to (100,300). Here's one way to do this: input1 = tf.reshape(input1, [100,300], name="reshaped_tensor") If you're not using TensorFlow but using Numpy, here's an implementation: input1 = np.array(input1) input1 = np.reshape(input1, (100,300)) Note: You might want to ...

0

It's difficult to say without knowing what your data looks like but from the numbers it seems too less and the images might be too similar to one another or very different. In any case, I'd have checked using other networks like Inception and decreasing learning rate even further (say 0.0001) to not mess with the Imagenet weights if your data is not very ...

2

Precision is the number of true positives over the number of predicted positives(PP), and recall is the number of true positives(TP) over the number of actual positives(AP) you get. I used the initials just to make it easier ahead. A true positive is when you predict a car in a place and there is a car in that place. A predicted positive is every car you ...

2

Look at Google's Open Image Dataset @ https://storage.googleapis.com/openimages/web/index.html They provide image-level labels, object bounding boxes, object segmentation masks, and visual relationships. Here is the link for the traffic signs dataset.

2

Neural networks can have a lot of different structures. CNNs can have a number of parameters that ranges from a few thousands to several millions. In general you aim to increase the number of filters and reduce the first 2 dimensions, as you go deeper in the network. So if you had Conv -> pool -> Conv -> pool -> ... , you could do for example ...

1

I found that the peak was caused by the data I am using. Specifically, the MinMaxScaler changed the data shape and I resolved the issue by simply dividing to the max value.

1

I think that front end refers to a high level API for a CNN framework (c++ front end, Python front end). The back end can be understood as a more peculiar (low level) interface to specific libraries. You can use different back ends but still manipulate training data and model building process the same way using the front end (use Keras with TensorFlow, ...

0

In such cases, you can have just 1 final neuron and treat the problem as a regression problem where the output distance from all 3 classes is calculated and the class with least distance becomes the predicted class. If you want independent values for 3 classes (such as [0.8, 0.5, 0.3]) which don't add up to 1, (something like multilabel/multiclass ...

1

You could maybe do something like this, it's a bit hackish $$y = C_1\cdot 1 + C_2 \cdot 0.5 + C_3 \cdot 0$$ $y$ represents the output and its bounded $\in [0, 1]$. $C_i$ is probability for class $i$. This way when $C_1 \approx 1, C_2 \approx 0, C_3 \approx 0$ you have y \approx 1\cdot 1 + 0.5 \cdot 0 + 0 \cdot 0 \...

Top 50 recent answers are included