I am studying this paper right now https://arxiv.org/pdf/2003.05863.pdf . And here is the code https://github.com/switchablenorms/DeepFashion_Try_On .
I faced a problem while training Clothes Warping Module. I tried about 42(!!!) times to train it tweaking hyperparameters and result is always the same - I get artifacts like in the picture below. enter image description here
Why do they appear? It looks as if I do not understand something crucial. Maybe the problem of artifacts in training GANs is covered somewhere.
Related
I have applied VGG16 to predict a classification problem. But the result was not good as I expected. So I applied U-Net separately to segment the region of interest. Now I want to merge these two codes like this, - If the image can segment the area of interest then it will give an output as 1, and if it can not then it will give an output as 0.
I need help regarding this. If you have any idea how o solve this problem please let me know.
I want to retrain the object detector Yolov4 to recognize figures of the board game Ticket to Ride.
While gathering pictures i was searching for an idea to reduce the amount of needed pictures.
I was wondering if more instances of an object/class in a picture means more "training per picture" which leads to "i need less pictures"
Is this correct? If not could you try to explain in simple terms?
On the roboflow page, they say that the YOLOv4 breaks detecting objects into two pieces:
regression to identify object positioning via bounding boxes;
classification to classify the objects into classes.
Regression (analysis) is - in short - a method of analysis that tries to find the data (images in your case) that is relevant. Classification - on the other hand - transforms the ‘interesting’ images from the previous step into a class (which is ’train piece’, ’tracks’, ’station’ or something else that is worth separating from the rest).
Now, to answer your question: “no, you need more pictures.” When taking more pictures, YOLOv4 is using more samples make / test a more accurate classification. Yet, you have to be careful what you want to classify. You do want the algorithm to extract a ’train’ class from an image, but not an ‘ocean’ class for example. To prevent this, make more (different) pictures of the classes you want to have!
I have some troubles after Forge model generation. The main goal is to get rvt model from JSON.
I have tested my code with Revit API in Revit. It works nice. But when add bundle to the Forge app and got rvt result - I have faced with weird glitch. I can`t see any wall in the project, but walls exist. I have checked with lookupRevit and saw walls and ids.
The question is "How to make invisible walls be visible?"
I have attached the recording demonstrating my glitch.
https://www.youtube.com/watch?v=WiZC2VLcVSc
Thanks
Please share the code for a minimal reproducible case so we can take a look. I am not aware of any way to achieve this result just creating a wall and saving the BIM. So, it will be interesting to see how you succeed with this feat.
Correction: a colleague spotted the problem in your video:
It looks like the walls were created in Phase 3, and the view phase is 1.
Copy-pasting them puts them on the active phase thus making them visible. (At least best I can tell from the video!)
I am trying to solve Baby detection with unet segmentation model. I already collected baby images, baby segments and also passed the adult images as negative (created black segments for this).
So if I will do in this way is unet model can differentiate the adults and babies? if not what I have to do next?
It really depends on your dataset.
During the training, Unet will try to learn specific features in the images, such as baby's shape, body size, color, etc. If your dataset is good enough (e.g. contains lots of babies examples and lots of adults with a separate color and the image dimensions are not that high) then You probably won't have any problems at all.
There is a possibility however, that your model misses some babies or adults in an image. To tackle this issue, There are a couple of things you can do:
Add Data Augmentation techniques during the training (e.g. random crop, padding, brightness, contrast, etc.)
You can make your model stronger by replacing Unet model with a new approach, such as Unet++ or Unet3+. According to Unet3+ paper, it seems that it is able to outperform both Unet & Unet++ in medical image segmentation tasks:
https://arxiv.org/ftp/arxiv/papers/2004/2004.08790.pdf
Also, I have found this repository, which contains a clean implementation of Unet3+, which might help you get started:
https://github.com/kochlisGit/Unet3-Plus
I have an image(e.g. 60x60) with multiple items inside it. Items are in the shape of square boxes, with say 4x4 dimensions, and are randomly placed within the image. The boxes(items) themselves are created with random patterns, some random pixels switched on and others switched off. So, it could be the same box repeated twice(or more in case of more than 2 items) in the image or could be entirely different.
I'm looking to create a deep learning model that could take in the original image(60x60) and output all the patches in the image.
This is all I have for now, but I can definitely share more details as the discussion starts. I'd be interested to weigh in different options that can help me achieve this objective. Thanks.
I would solve this using object detection. First I would train a network to detect those box like objects by cutting out patches of those objects. Then I would run a Faster R-CNN or something like this on it.
You might want to take a look at the stanford lecture on detection (slides here: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture11.pdf).