-
I have red the part where it's explained how to train the model using your own dataset. However, it doesn't tell how and where to put the training images.
There is a mention of the dataset here: _fl…
-
Thanks for your great works : )
As mentioned in your UFO^2 paper, ResNet-50 model perform relative well on COCO wsod task (ECCV paper P11 Table 3.). But the cfg file of ResNet-50 model seems not ap…
-
The CRAFT authors used a weakly-supervised training method to handle the fact that most datasets don't annotate at the character level. I saw in your [docs](https://keras-ocr.readthedocs.io/en/latest/…
-
## Before you post a new issue - you must first check the following (and check the boxes with an "X" below)
- [ x] 1.) Can you login using the smartphone app Volkswagen/Volkswagen Connect and intera…
-
Firstly, thank you for your excellent work. When using these released video data and labels, I have met two key troubles. Hope you can give me some help and suggestions.
* 1. How to get the accurat…
-
If few images are partially annotated then you can do supervised learning.
I would think that given an integer_mask_annotation:
1. compute target bounding boxes, centroid and width/height (using …
-
Hi, I think this is a really good unsupervised learning model, my question is that I know the current implementation is for single label with 1 label for 1 image, is it possible to extend it and apply…
-
Dear Spyros Gidaris, Praveer Singh and Nikos Komodakis,
i have read your paper "Unsupervised Representation Learning by Predicting Image Rotations" and was impressed by your work and the astonishi…
-
In order to eliminate the need for the NMS, we adopt a
similar strategy for center localization. Specifically, we further
consider the aspect ratio of the box in the Gaussian kernel
since the strat…
-
I tried training for Weak supervision using the SynthText Strong supervision model on a custom data set.
I trained for just three epochs with 1000 iterations each but when I use the models that get…