-
I want to reproduce your code and want to run it on Visual Genome1.4 dataset. However, I cannot find the corresponding TXT file for train, val, and test when loading the dataset. Can you put these thr…
-
if the image 's size are variable,the output image's size are variable too，so how to build this nn
ghost updated
6 years ago
-
Good afternoon,
I got another question concerning practice#1. When designing the model, we have to determine the different sizes of the output of the convolutional layers + pooling. We especially …
-
## Paper
- [paper](https://arxiv.org/abs/1812.05050)
- [code](https://github.com/foolwood/SiamMask)
- [project](http://www.robots.ox.ac.uk/~qwang/SiamMask/)
-
Hi @AlexeyAB
I am just curious as to how YOLOv3 can easily change its network input size without retraining it. For example, I train the model with 416x416. I can still do inference with 512x512 or…
-
Hi,
Thanks for your shared codes and I learned so much out of it!
I'm going to modify your wae implementation for 1D sequential data (protein sequences reconstruction), However, your codes are …
-
### Semantic Segmentation
- No objects, just pixels
- Input: Image
- Output: the …
hon9g updated
5 years ago
-
### Feature Name
To enhance the Deep Learning Playground's audio data processing capabilities, we aim to integrate the M5 network architecture, inspired by the M5 network. This architecture is crucia…
-
-
Hi, the default argument for --keep_res is False. Are these outputs of the bounding box locations based on the original resolution or the resized resolution? Will it scale back? How do you deal with s…