Limin Zhang

images during training are too dark

4

Hi, thanks for sharing your great work! I follow your recommendation that use the [The Paris Dataset](http://www.robots.ox.ac.uk/~vgg/data/parisbuildings/) to train the network. After training, when I check the `result/train/real` or `result/train/cropped`...

Model performance and image size during the test phase

3

Hi, Thank you for your work! I want to ask two questions： - 1. Are you training on the author's data set and how does the model perform? - 2....

Thanks for your great work! I read your code carefully, my question are as follows: - Can you upload the pretrained model for the encoder? This will make it easier...

关于label生成的疑问

6

您好，对于label生成部分的代码，存在一些疑问，询问一下。 对于`siamfc.py`中的函数`_create_labels(self, size)`部分，存在如下代码： ```Python r_pos = self.cfg.r_pos / self.cfg.total_stride r_neg = self.cfg.r_neg / self.cfg.total_stride labels = logistic_labels(x, y, r_pos, r_neg) ``` 其中，在该代码的默认配置中：`cfg.r_pos = 16`,`cfg.r_neg = 0`,`cfg.total_stride = 8`。 我的疑问： -...

I want to test `OneShot AllReduce` and `TwoShot AllReduce` separately, so I have modified the following code: ``` class LLaMAModel(Module): def __init__(self, config: PretrainedConfig) -> None: super().__init__() init_all_reduce_helper() self.mapping =...

How to set the initial kv cache length?

2

I want to test an example: the initial kv cache length is 2048, and LLM iterate 2048 times, so the output_tokens=2048, but the initial kv cache length is 2048, and...