cfanyyx

Results 10 issues of cfanyyx

Thanks for your nice codes, and I have two questions about the yolo weight file: 1. In your load_weight function, you read the weights in the order of 'gamma, beta,...

In some of my output images, there are strange patterns occurred like the pics below: ![image](https://user-images.githubusercontent.com/7723243/51155055-2c1eba00-18b1-11e9-95ac-033966b6b37f.png) ![image](https://user-images.githubusercontent.com/7723243/51155091-4fe20000-18b1-11e9-814d-6e2df82cc7c1.png) ![image](https://user-images.githubusercontent.com/7723243/51155129-6b4d0b00-18b1-11e9-91b1-1f204e277de8.png) I can't figure out why those things came out upon my output...

Thanks for this work. I want to know how to make the generated image more like its training data, especially the style?

![image](https://user-images.githubusercontent.com/7723243/127610966-6fc5d640-193b-413e-8a46-6b04a2286cac.png) ![image](https://user-images.githubusercontent.com/7723243/127611160-b58375ae-0c18-46d2-9a9c-f152e4a0e5b0.png) ![image](https://user-images.githubusercontent.com/7723243/127611275-a730d181-665d-42a9-91d3-e5c3e4fbcc2c.png)

I used the default settings and params. After training on my own datasets, in some of my test output images using the saved model, there are strange green areas on...

发现如果按照下面这样写貌似不太对,传进去之后,inputDims的nbDims会是一个随机数的样子: `inputDims_field = trt.PluginField("inputDims", np.array([16, 8, 8]), trt.PluginFieldType.DIMS)`

After merging, what is the instance prompt?

Did this model also train with ID Loss?