fix split of train,test
This commit is contained in:
parent
e01c006fa9
commit
dbfbe71602
@ -199,7 +199,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -1,5 +1,5 @@
|
||||
# -*- coding: UTF-8 -*-
|
||||
# !/usr/bin/python
|
||||
# @time :2019/8/28 14:13
|
||||
# @time :2019/10/13 9:00
|
||||
# @author :Mo
|
||||
# @function :
|
46
keras_textclassification/data_preprocess/data_split.py
Normal file
46
keras_textclassification/data_preprocess/data_split.py
Normal file
@ -0,0 +1,46 @@
|
||||
# -*- coding: UTF-8 -*-
|
||||
# !/usr/bin/python
|
||||
# @time :2019/10/13 8:07
|
||||
# @author :Mo
|
||||
# @function :数据切分为训练集,验证集
|
||||
|
||||
|
||||
from sklearn.model_selection import StratifiedKFold
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
|
||||
from keras_textclassification.data_preprocess.text_preprocess import txt_write
|
||||
|
||||
|
||||
def data_kfold(path_org_data, k_fold_split=10, path_save_dir=""):
|
||||
"""
|
||||
切分训练-测试集
|
||||
:param path_org_data: str, 原始语料绝对路径地址,utf-8的csv格式
|
||||
:param k_fold_split: int, k折切分, 原始语料中每个类至少有k_fold_split条句子
|
||||
:param path_save_dir: str, 生成训练集-测试集文件的保存目录
|
||||
:return:
|
||||
"""
|
||||
label_ques = pd.read_csv(path_org_data, names=["label","ques"], usecols=["label","ques"])
|
||||
quess = label_ques["ques"].values.tolist()[1:]
|
||||
labels = label_ques["label"].values.tolist()[1:]
|
||||
|
||||
quess, labels = np.array(quess), np.array(labels)
|
||||
kf_sp = StratifiedKFold(n_splits=k_fold_split)
|
||||
|
||||
for train_index, dev_index in kf_sp.split(quess, labels):
|
||||
train_x, train_y = quess[train_index], labels[train_index]
|
||||
dev_x, dev_y = quess[dev_index], labels[dev_index]
|
||||
lq_train = [train_y[i].replace(",",",").strip() + "," + train_x[i].replace(",",",").strip() + "\n"
|
||||
for i in range(len(train_y))]
|
||||
lq_valid = [dev_y[i].replace(",",",").strip() + "," + dev_x[i].replace(",",",").strip() + "\n"
|
||||
for i in range(len(dev_y))]
|
||||
txt_write(["label,ques\n"] + lq_train, path_save_dir + "lq_train.csv")
|
||||
txt_write(["label,ques\n"] + lq_valid, path_save_dir + "lq_valid.csv")
|
||||
break
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
from keras_textclassification.conf.path_config import path_root
|
||||
filepath = path_root + "/data/baidu_qa_2019/baike_qa_train.csv" # 原始语料
|
||||
k_fold_split = 10
|
||||
data_kfold(path_org_data=filepath, k_fold_split=10, path_save_dir=path_root+ "/data/baidu_qa_2019/")
|
@ -129,7 +129,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
if __name__=="__main__":
|
||||
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -90,7 +90,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -129,7 +129,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
if __name__=="__main__":
|
||||
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -97,7 +97,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -128,7 +128,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -82,7 +82,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -119,7 +119,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
# pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
# pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -98,7 +98,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -97,4 +97,4 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
@ -117,7 +117,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -84,7 +84,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -117,7 +117,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -93,7 +93,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -117,7 +117,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -86,7 +86,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -117,7 +117,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -90,7 +90,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -98,7 +98,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -93,7 +93,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.001) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -91,7 +91,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
train(rate=0.001) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -86,7 +86,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
train(rate=0.001) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -90,7 +90,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -90,7 +90,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -118,7 +118,7 @@ def pred_input(path_hyper_parameter=path_hyper_parameters):
|
||||
|
||||
if __name__=="__main__":
|
||||
# 测试集预测
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
pred_tet(path_test=path_baidu_qa_2019_valid, rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
|
||||
# 可输入 input 预测
|
||||
pred_input()
|
||||
|
@ -95,7 +95,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
train(rate=0.01) # sample条件下设为1,否则训练语料可能会很少
|
||||
train(rate=1) # sample条件下设为1,否则训练语料可能会很少
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -84,7 +84,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -82,7 +82,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -81,7 +81,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -82,7 +82,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -85,4 +85,4 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
|
@ -81,7 +81,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
@ -81,7 +81,7 @@ def train(hyper_parameters=None, rate=1.0):
|
||||
|
||||
|
||||
if __name__=="__main__":
|
||||
train(rate=0.01)
|
||||
train(rate=1)
|
||||
# 注意: 4G的1050Ti的GPU、win10下batch_size=32,len_max=20, gpu<=0.87, 应该就可以bert-fineture了。
|
||||
# 全量数据训练一轮(batch_size=32),就能达到80%准确率(验证集), 效果还是不错的
|
||||
# win10下出现过错误,gpu、len_max、batch_size配小一点就好:ailed to allocate 3.56G (3822520832 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY: out of memory
|
||||
|
Loading…
Reference in New Issue
Block a user