-
## 🚀 Feature
I have been using Detectron2 for 3 months. I have tried nearly all the data augmentation techniques which are provided out-of-the-box by Detectron2. I would like to propose a new data au…
-
Image data augmentation is a technique to increase the size of the training dataset. This is useful when there is less training data to train.
-
Question about data augmentation: When subgraph augmentation is performed, essentially only the enge_index is modified. This means that only the subgraph is aggregated for information propagation. Wha…
-
We want to be able to augment existing noise-free locust simulation data to create larger datasets out of that in a consistent way.
- Addition of noise (different types)
- Shifts in time
- Varia…
-
请问这里的transformation为什么要 -8 ?
https://github.com/bilylee/SiamFC-TensorFlow/blob/master/datasets/dataloader.py#L38
另外，因为下面的处理，instance embeds的shape永远都是[batch_size, 255-2*8, 255-2*8, 3]吗？
https://gi…
-
This came up as I was working on #37. It may be useful to include a function for generating "new" samples by adding noise to existing samples, then running the newly generated sample through the featu…
-
Hi, is data augmentation allowed ? Can we generate some augmented data (like GAN) to train the model by using the proposed dataset?
-
I was looking at [`yolov3.cfg`](https://github.com/AlexeyAB/darknet/blob/6390a5a2ab61a0bdf6f1a9a6b4a739c16b36e0d7/cfg/yolov3.cfg) for data augmentation parameters and could only find HSV values and an…
-
When doing data augmentation, the author uses tf.image.sample_distorted_bounding_box and sets the min_object_covered as 0.1 as well as area range between (0.08, 1.0). Would this setting (min_object_co…
-
Thanks for your code, it helps me a lot. But I have some questions about data augmentation. In the `generate_train_lap_pry.m`, you only used downsizing to make more training data. While in the paper, …