enter image description hererencve
In Figure.3 a block diagram of a certain system is shown with input 𝑥(𝑛) and output 𝑦(𝑛). a. Find the difference equation that relates input to output. b. Find the system transfer function 𝐻(𝑧).
Related
First sorry for my bad english.
Short version :Can anyone tell me how to use only the first n layers of XLNET for classification ?
Long Version :
I have a dataset composed of texts and their summary. The goal is to detect if the summary is generated by a bot or not.
So I thought of using bert and give him as input "[CLS] "+Text+" [SEP]"+summary then take the representation of the "[CLS] " token and detect using a classifier if the summary was written by a bot.
Th problem is bert takes no more than 512 words as input.
So I thought of using XLNET. But here another problem appeared : My gpu (RTX 2060) can't handle a batch of size 1.
So I Thought of using only like the first 4 layers of XLNET but the problem is: I don't know how to do it.
So my code to load the model is model=XLNetForSequenceClassification.from_pretrained("xlnet-base-cased", num_labels = 2)
can anyone tell me what to add to use only a part of the network please ?
I want to detect digits on a display. For doing that I am using a custom 19 classes dataset. The choosen model has been yolov5-X. The resolution is 640x640. Some of the objets are:
0-9 digits
Some text as objects
Total --> 17 classes
I am having problems to detect all the digits when I want to detect 23, 28, 22 for example. If they are very close to each other the model finds problems.
I am using roboflow to create diferent folders in which I add some prepcocessings to have a full control of what I am entering into the model. All are checked and entered in a new folder called TRAIN_BASE. In total I have 3500 images with digits and the majority of variance is with hue and brightness.
Any advice to make the model able to catch all the digits besides being to close from each other?
Here are the steps I follow:
First of all, The use of mosaic dataset was not a good choice the purpose of detecting digits on a display because in a real scenario I was never gonna find pieces of digits. That reason made the model not to recognize some digits if it was not shure.
example of the digits problem concept
Another big improvement was to change the anchor boxes of the yolo model to adapt them to small objects. To know which anchor boxes I needed. Just with adding this argument to train.py is enought in the script provided by ultralitics to print custom anchors and add them to your custom architecture.
To check which augmentations can be good and which not, the next article explains it quite visually.
P.D: Thanks for the fast response to help the comunity gave me.
I'm trying to get Autoware to send out a tracked-object list for the LGSVL Simulation. I turn on Yolo3, Euclidian Cluster detection, then pixel_cloud_fusion. When I do, it constantly states that it's looking for TF and Intrinsics data. Looking further, this seems to be a "camera_info" topic that is missing. So I made one up just trying to get it working (not sure if LGSVL has any kind of native support??). I used a bunch of 1s for the matrices and "plumb bob" for the type and matched the width/height to the published camera images. Once I send it, however, I get the error:
[pixel_cloud_fusion] "camera" passed to lookupTransform argument target_frame does not exist
I have no idea what this means and the text does not appear in the Autoware software. Am I doing something wrong? Is there another topic I'm lacking?
P.S Maybe someone with 1500 rep should create an Autoware tag
It seems like this might be an issue with the TF tree being incomplete. For loopup transform to work it needs a well defined TF tree to whatever other fixed frame. To add your camera to the TF tree you should be able to use the static transform publisher.
Suppose there is a data set of statistical data with a number of input columns and one output column. The predictors characterize some particular process that is repeated, so one data row is corresponding to one occasion of that process. And for these process characteristics the order and duration is important. Some of them might be absent at all, some of them are repeated, but with different speed or other parameter.
Let's say that our process is names P and it can have a lot of child parts, that form the process together. Let's say, once the process had N sub processes:
Sub process 1, with: speed = SpdA, duration = DurA, depth = DepA
Right after sub process A next sub process B happened:
Sub process 2, with: speed = SpdB, duration = DurB, depth = DepB
...
... N. Sub process N.
So there might be from 1 to N child processes in each process, that is, in each data row. And the amount of the child processes may vary from one row to another. This is about the input data.
As for the output - the output here in the simplest case is binary - either success or failure, but in reality it will be a positive number starting from 0 to positive infinity. This number represents the time by which the process has finished successfully. If the value for the output is a positive infinity - it means that the process failed to succeed.
Very important note, if we are going with the simplest case where the output is binary - in the statistical data set there will be data rows that mostly have failure in the output. The goal is to find the hypothetical parameters that values of the test predictors should be equal to, to make the process succeed.
For example, after learning we should be able to tell what is the concrete universal input parameters that will most process success. That was the simplest, binary output case.
However, in real life we will have the output that represents time by which the process finished successfully, and +infinity - if failure. So here the goal is the same - make the process succeed or as much close to success as possible. The goal is to generate the test inputs that we might use in future to prevent the output equal to +infinity.
The goal maximum is, having the target time provided, find the exact values for the inputs that will make the process finish successfully as closer to the given time as possible. Here we should expect the enumeration of child processes, their order and the values for each child process to be predicted.
Here in this problem, I guess, the output will play the role of the input and the input will play the role of the output.
What is the approach to solve these problems? How to handle the variable number of characteristics and how to handle the order that might vary in the each data row?
I am a novice in machine learning and would appreciate the concrete suggestions or examples of similar problems solved.
Any help and advice welcome!
I'm working on a suggestion system. For a given input, the system outputs N suggestions.
We have collected data about what suggestions the users like. Example:
input1 - output11 output12 output13
input2 - output21
input3 - output31 output32
...
We now want to evaluate our system based on this data. The first metric is if these outputs are present in the suggestions of our system, that's easy.
But now, we would like to test how well positioned are these outputs in the suggestions. We would like to have the given outputs close to the first suggestions.
We would like a single score for the system or for each input.
Based on the previous data, here is what a score of 100% would be:
input1 - output11 output12 output13 other other other ...
input2 - output21 other other other other other ...
input3 - output31 output32 other other other other ...
...
(The order of output11 output12 output13 is not relevant. What is important is that ideally the three of them should be in the first three suggestions).
We could give a score to each position that is hold by a suggestion or count the displacement from the ideal position, but I don't see a good way to do this.
Is there an existing measure that could be used for that ?
You want something called the mean average precision (it's a metric from information retrieval).
Essentially, for each of the 'real' data points in your output list, you can compute the precision (#of correct entries above that point / #entries above that point). If you average this number across the positions of each of your real data points in the output list, you get a metric that does what you want.