I am actually working with DCGAN (Py-Torch implementation), and the output is always a 64-sized grid of artificial images per epoch. I would like to increase such number, but do not know (I do not know which parameter to change, but I tried to check the code without success).
Does anyone have some idea of how to do that?
The entire Py-Torch implementation of DCGAN can be found in the following link:
https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html
Change this value of below parameters to whatever the size of image you would want as output
Size of feature maps in generator
ngf = 64
Size of feature maps in discriminator
ndf = 64
Related
I am using the Edit2D extension on an svf created from a 2D dwg file and have a question about transforms. The Autodesk.Edit2D.Polygon's that are created have a getArea() method which is great. However it's not in the correct unit scale. I tested one and something that should be roughly 230sf in size is coming back as about 2.8.
I notice that the method takes an argument of type Autodesk.Edit2D.MeasureTransform which I'm sure is what I need, however I don't know how to get that transform. I see that I can get viewer.model.getData().viewports[1].transform. However, that is just an array of 16 numbers and not a transform object so it creates an error when I try to pass it in.
I have not been able to find any documentation on this. Can someone tell me what units this is coming back in and/or how to convert to the same units as the underlying dwg file?
Related question, how do I tell what units the underlying DWG is in?
EDIT
To add to this, I tried to get all polylines in the drawing which have an area property. In this case I was able to figure out that the polyline in the underlying dwg was reporting its area in square inches (not sure if that's always the case). I generated Edit2D polygons based on the polylines so it basically just drew over them.
I then compared the area property from the polyline to the result of getArea() on the polygon to find the ratio. In this case it was always about 83 or 84 times smaller than the square foot value of the polyline it came from (there is some degree of error in my tracing system so I don't expect they would be exact at this point). However, that doesn't fit any unit value that I know of. So remaining questions:
What unit is this?
Is this consistent or do I need to look somewhere else for this scale?
Maybe you missed the section 3.2 Units for Areas and Lengths of https://forge.autodesk.com/en/docs/viewer/v7/developers_guide/advanced_options/edit2d-use/
If you use Edit2D without the MeasureExtension, it will display all coordinates in model units. You can customize units by modifying or replacing DefaultUnitHandler. More information is available in the Customize Edit2D tutorial.
and https://forge.autodesk.com/en/docs/viewer/v7/developers_guide/advanced_options/edit2d-customize/
BTW, we can get the DefaultUnitHandler by edit2dExt.defaultContext.unitHandler
Ok after a great deal of experimentation and frustration I think I have it working. I ended up looking direction into the js for the getArea() method in dev tools. Searching through the script, I found a class called DefaultMeasureTransform that inherits from MeasureTransform and takes a viewer argument. I was able to construct that and then pass it in as an argument to getArea():
const transform = new Autodesk.Edit2D.DefaultMeasureTransform(viewer);
const area = polygon.getArea(transform);
Now the area variable matches the units in the original cad file (within acceptable rounding error anyway, it's like .05 square inches off).
Would be nice to have better documentation on the coordinate systems, am I missing it somewhere? Either way this is working so hopefully it helps someone else.
I'm new to deep learning and trying cell segmentation with Detectron2 Mask R-CNN.
I use the images and mask images from http://celltrackingchallenge.net/2d-datasets/ - Simulated nuclei of HL60 cells - the training dataset. The folder I am using is here
I tried to create and register a new dataset following balloon dataset format in detectron2 colab tutorial.
I have 1 class, "cell".
My problem is, after I train the model, there are no masks visible when visualizing predictions. There are also no bounding boxes or prediction scores.
A visualized annotated image is like this but the predicted mask image is just a black background like this.
What could I be doing wrong? The colab I made is here
I have a problem similar to yours, the network predicts the box and the class but not the mask. The first thing to note is that the algorithm automatically resizes your images (DefaultTrainer), so you need to create a custom mapper to avoid this. Second thing is that you need to create a data augmentation, using which you significantly improve your convergence and generalization.
First, avoid the resize:
cfg.INPUT.MIN_SIZE_TRAIN = (608,)
cfg.INPUT.MAX_SIZE_TRAIN = 608
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING = "choice"
cfg.INPUT.MIN_SIZE_TEST = 608
cfg.INPUT.MAX_SIZE_TEST = 608
See too:
https://gilberttanner.com/blog/detectron-2-object-detection-with-pytorch/
How to use detectron2's augmentation with datasets loaded using register_coco_instances
https://eidos-ai.medium.com/training-on-detectron2-with-a-validation-set-and-plot-loss-on-it-to-avoid-overfitting-6449418fbf4e
I found a current workaround by using Matterport Mask R-CNN and the sample nuclei dataset instead: https://github.com/matterport/Mask_RCNN/tree/master/samples/nucleus
i have trained a model on GTSRB(german traffic sign dataset)it has approx 39K pictures of sizes vary from 16x16 to 128x128 for 43 classes.Training accuracy=97% , validation accuracy=91% . But when i predcit any image of my own , it never recognize correctly.Below is my code pictures
Libraries and accessing data is shown.i have also tried other way without using imagedatagenerator but same problem
here is my model. I also tried it with input shape(64,64) but same problem
here is how i am predicting my images
here is my model.fit results with loss and acc. %
I need to render some points with specified size using ShapeRenderer.
When using GL20, Gdx.gl and Gdx.gl20 will be initialized, while Gdx.gl10 and Gdx.gl11 will be null.
I can set line width and render using code such as this:
Gdx.gl.glLineWidth(5);
mShapeRenderer.begin(ShapeType.Rectangle);
mShapeRenderer.rect(0.0f, 0.0f, 50.0f, 50.0f);
mShapeRenderer.end();
But, from what I figured out, I can only set point size using Gdx.gl10.glPointSize(5) or Gdx.gl11.glPointSize(5) - which won't work in my case since both gl10 and gl11 are null.
Are there any simple solutions to this problem?
OpenGL ES dropped support for glPointSize (among other things) in 2.0, that's why you can't find it in Gdx.gl20, or in Gdx.gl.
Instead of setting a point size, just use ShapeRenderer's filledCircle to render the "large" points. (I would point to the API documentation, but they just changed the API last week and I'm not sure which version you are using.)
I'm writing a program for a college course. I import a .PPM file saved as a 2-d array from main into the function. Then I have to update the pixels of a graphics window (which is opened in main) using .setPixel and color_RGB() method and functions.
The pixels are updating, however there is a white pixel in between each colored pixel for some reason. It's not the PPM file (they were supplied by my professor and I've tried multiple ones), so it has to be my function.
Warning: I am not allowed to use anything in my program that we have not yet covered in our course (it's a first year, 4 month course so the scope is not massive). I don't need to know exactly HOW to fix it, as much as I need to know why it's doing it (AKA: I need to be able to explain how I fixed it, and why it was breaking in the first place).
Here is my function:
def Draw_Pic(pic,pic_array, sizeX, sizeY, gfx_window):
for y in range(sizeY):
for x in range(0, sizeX, 3):
pixel_color = color_rgb(pic_array[y][x],pic_array[y][x+1],pic_array[y][x+2])
pic.setPixel(x,y,pixel_color)
gfx_window.update()
You are using range(0, sizeX, 3) which creates a list with values 0 to sizeX with increment 3.
So your x goes 0..3..6..9 etc. Makes perfect sense for the part where you assemble pixel color from 3 components, but then you do pic.setPixel(x,y,colors) using the same interleaved x.
Hope that helped.
P.S. By the way, why "colors" and not "color"?
edit Also, that way you'll copy only 1/3 of the image in pic_array.