Yulong Ma

Results 4 comments of Yulong Ma

我的做法:修改zip_data()、data_generator、和模型结构(从keras.layers导入Input和Concatenate) ![image](https://user-images.githubusercontent.com/69295068/173585037-bb54e4d9-a957-414d-aee2-3d4c6c310681.png) ![image](https://user-images.githubusercontent.com/69295068/173584976-bf134ade-cefc-4096-acb5-8f036bef94fa.png) ![image](https://user-images.githubusercontent.com/69295068/173585078-6ddcb13d-2ed4-42b9-835f-a270a116939a.png) 训练代码无需修改,用这种方式我跑通了。刚学的keras,应该还有更好的方法。

已自行解决问题,可爬取每个链接后及时储存数据。 解决方案:修改piplines.py中的【class WeibocrawlerPipeline(object)】如下 def process_item(self, item, spider): base_dir = '结果文件' if not os.path.isdir(base_dir): os.makedirs(base_dir) file_path = base_dir + os.sep + 'Userinfo' + '.csv' if not os.path.isfile(file_path): is_first_write = 1 else:...

> Hello! Could you provide more details on your environment? It's difficult for us to replicate the error otherwise. Thanks! > > Silvia **Hi! Silvia.** When I was training CTM...