xiuzhilu

Results 8 issues of xiuzhilu

My model is defined as follows: def create_model(): #input input_layer=Input(shape=(max_squence_len,),name="x_seq") embedding_layer=Embedding(input_dim=max_token_num,output_dim=embedding_dim) (input_layer) #conv layers convs=[] filter_sizes=[2,3,4] for fs in filter_sizes: l_conv=Conv1D(filters=50,kernel_size=fs,activation="relu")(embedding_layer) l_pool=MaxPooling1D(pool_size=2)(l_conv) l_pool=Flatten()(l_pool) convs.append(l_pool) merge=concatenate(convs,axis=1) out=Dropout(0.5)(merge) output=Dense(32, activation='relu')(out) output=Dense(units=31, activation='softmax')(output)...

感谢大佬的分享,不过大佬我想问一下,为什么的把模型下载到本地来调用与直接用的huggingface的API结果不一样呢?是huggingface的API部署的模型跟公开的出来的这个模型不是同一个嘛?他们好像实验的时候,得到的答案跟huggingface上的答案也是不一样的https://github.com/basketballandlearn/MRC_Competition_Dureader/issues/39

rasa sever,action sever,sever都启动之后,提交请求(curl -H "Content-Type:application/json" -X GET http://127.0.0.1:8088/ai?content=我想知道明天的天气),回复并不是查询天气,而是"没听懂,请换种说法吧~",说明系统根本就没有理解请求的内容,看了一下log,action sever 里执行的都是action_default_fallback,这是为何

I train roberta and xlnet with PIE Synthetically a1(train:8865347 dev:3000), The parameters of the first stage model are as you provided them in Git(https://github.com/grammarly/gector/blob/master/docs/training_parameters.md). The training parameter and I get...

作者你好,可以麻烦你再把整个代码的执行过程再细化一下嘛?比如先是下载数据集,首先下载数据集需要配置那些配置文件,然后去执行那些脚本,数据下载之后放在什么位置,解压数据,然后是数据预处理,需要配置那些配置文件,然后再执行那些脚本,得到什么结果等等。可能是我自己太菜了,希望能够得到一个傻瓜式的教程。先谢谢作者

感谢作者公开,我在数据预处理的时候,我把预训练所用的数据都下载好,并使用cat 32-lang-pairs.tar.* | tar -xzf - 去解压,我在执行bash ${PROJECT_ROOT}/preprocess/multilingual_preprocess_main.sh ${config_yaml_file}时,${config_yaml_file}选择的是${PROJECT_ROOT}/experiments/example/configs/preprocess/train.yml, 请问,在train.yml中,raw_data_path是预训练数据下载后所放在的目录是吗?后边的merged_output_path,output_main_path....dict_path等各种路径,可以自己自定义是嘛?@linzehui

Hi,dear. I download dataset wmt14 en-de, and when I run the script "sh sh_train.sh", I meeting the ERROR:Process 0 terminated with the following error: Traceback (most recent call last): File...

Hi, dear. Thank you for your sharing. According to the code you gave when I used multi-GPU training, it is equivalent to torch.nn. data_parallel. If I want to achieve distributed...