dh12306
dh12306
when i cloned this project , i run ' start-hadoop-spark-workbench-with-Hive.sh' , then there are some CONTAINERs running, but when i 'docker exec -it spark-master /bin/bash' , and cd spark/bin ,...
用测试脚本 得到的png如下图,使用pil读取的时候是 rgb模型,没有alpha通道  怎么通过原图获取想要的抠图区域呢,实现 origin.paste(mask, (0,0), mask= a) @xuebinqin 
@JizhiziLi @chaimi2013 运行的是test_samples 
如题,训练了5个epoch,生成submit时,发现第79行的预测有问题,因为max_seq_len=200,当文本长度大于200时,预测结果只有198个,submit的样本最大长度436,当改了max_seq_len的时候,就会报错,大概是维度不匹配的错,如下图,想请教下@wenyu332 大神这个max_seq_len 改了之后还需要改哪里: gpu 报错如下:  cpu 报错如下: 
效果不太好啊
这是我用您训练好的G生成的,原图跟这个一样,没什么变化,需要加大训练数据集继续训练么? 
I tried this prompt but didn't work well : ``` The following are multiple choice questions (with answers) about abstract algebra. ========example====== In order to make the title of this...
### Describe the feature 测试集不通过,报错如下: ``` 6%|▋ | 117/1871 [30:11
下载了5b的 diffusers版 ,文件大概40g, [https://huggingface.co/THUDM/CogVideoX-5b](url) 但是为什么加载之后生成的时候,显存只用了4g左右,是不是没加载对?  启动用这个,python gradio_web_demo.py
#### the first error is that login was blocked, and I try again after a while ,the problem seems to be solved ``` Traceback (most recent call last): File "E:\crawler\twikit\examples\mytest.py",...