something wrong with the parameters when config the BLSTM

[hongyuK]

There is a ValueError when I git down all the code and run the code follow the guidance.
Traceback is follow:

Traceback (most recent call last): File "vuldeepecker.py", line 100, in main() File "vuldeepecker.py", line 95, in main blstm = BLSTM(df,name=base) File "D:\vuldetect\dataset\VulDeePecker-master\VDPython-master\blstm.py", line 40, in init test_size=0.2, stratify=labels[resampled_idxs]) File "F:\Anaconda\envs\tensorflow\lib\site-packages\sklearn\model_selection_split.py", line 2100, in train_test_split
default_test_size=0.25) File "F:\Anaconda\envs\tensorflow\lib\site-packages\sklearn\model_selection_split.py", line 1782, in _validate_shuffle_split
train_size) ValueError: With n_samples=0, test_size=0.2 and train_size=None, the resulting train set will be empty. Adjust any of the aforementioned parameters.

[ckt0325]

I found an error in lines 32 and 33 of blstm.py.
The data of vectors and labels are reversed.

vectors = np.stack(data.iloc[:, 1].values)             0
labels = data.iloc[:, 0].values                              1 

[lyqssb]

I got the same error
ValueError: With n_samples=0, test_size=0.2 and train_size=None, the resulting train set will be empty. Adjust any of the aforementioned parameters.
Don't know how to fix it? @ckt0325 have you correct it?

[ckt0325]

Vectors is the first column of data, labels is the second column of data.

Original codes:
vectors = np.stack(data.iloc[:, 1].values)
labels = data.iloc[:, 0].values
Modified codes:
vectors = np.stack(data.iloc[:, 0].values)
labels = data.iloc[:, 1].values
Hope my advice can help you.
@lyqssb

[lyqssb]

@ckt0325 it works now ! thank you so much!!!!

[ckt0325]

You are welcome. I once read this code, if you have any problem, we can study it together. And this is my email: 2898984956@qq.com

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人:&nbsp;"lyqssb"<notifications@github.com&gt;; 发送时间:&nbsp;2020年5月14日(星期四) 下午3:26 收件人:&nbsp;"johnb110/VDPython"<VDPython@noreply.github.com&gt;; 抄送:&nbsp;"David"<2898984956@qq.com&gt;;"Mention"<mention@noreply.github.com&gt;; 主题:&nbsp;Re: [johnb110/VDPython] something wrong with the parameters when config the BLSTM (#1) @ckt0325 it works now ! thank you so much!!!! — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[lyqssb]

@ckt0325 My pleasure~ thanks!

[lily79]

Vectors is the first column of data, labels is the second column of data.

Original codes:
vectors = np.stack(data.iloc[:, 1].values)
labels = data.iloc[:, 0].values
Modified codes:
vectors = np.stack(data.iloc[:, 0].values)
labels = data.iloc[:, 1].values
Hope my advice can help you.
@lyqssb

看你留的联系方式是qq，所以猜你也是国内的哈，就用中文说了，我也发现了这个问题，也是按照你一样改的，改完调试还是会报错，报的错误是：
Traceback (most recent call last):
File "/root/.pycharm_helpers/pydev/pydevd.py", line 1741, in
main()
File "/root/.pycharm_helpers/pydev/pydevd.py", line 1735, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "/root/.pycharm_helpers/pydev/pydevd.py", line 1135, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/root/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/tmp/pycharm_project_295/vuldeepecker.py", line 101, in
main()
File "/tmp/pycharm_project_295/vuldeepecker.py", line 97, in main
blstm.train()
File "/tmp/pycharm_project_295/blstm.py", line 75, in train
self.model.fit(self.X_train, self.y_train, batch_size=self.batch_size, epochs=4, class_weight=self.class_weight)
File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/engine/training.py", line 66, in _method_wrapper
return method(self, *args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/engine/training.py", line 802, in fit
data_handler = data_adapter.DataHandler(
File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/engine/data_adapter.py", line 1116, in init
if class_weight:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

你遇到这个问题了没？你是咋改的？谢谢啦！
我的联系方式35248934，申请加你了
@ckt0325

[lily79]

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

解决了，有人遇到了一样的问题，应该是class_weights参数用错，当其是一个 numpy array的时候，用 sample_weight参数穿这个值，不要用 class_weight 这个参数，在keras的_make_class_weight_map_fn函数里，class_weight接受的是字典对象。
https://stackoverflow.com/questions/62913700/valueerror-the-truth-value-of-an-array-with-more-than-one-element-is-ambiguous

[lily79]

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

解决了，有人遇到了一样的问题，应该是class_weights参数用错，当其是一个 numpy array的时候，用 sample_weight参数穿这个值，不要用 class_weight 这个参数，在keras的_make_class_weight_map_fn函数里，class_weight接受的是字典对象。
https://stackoverflow.com/questions/62913700/valueerror-the-truth-value-of-an-array-with-more-than-one-element-is-ambiguous

这么改还是会报错，所以，直接把class_weight改为字典类型传进去：
self.model.fit(self.X_train, self.y_train, batch_size=self.batch_size, epochs=4, class_weight=self.class_weight)
改为：
self.model.fit(self.X_train, self.y_train, batch_size=self.batch_size, epochs=4, class_weight=dict(enumerate(self.class_weight)))
解决啦！

[foresta-yang]

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

解决了，有人遇到了一样的问题，应该是class_weights参数用错，当其是一个 numpy array的时候，用 sample_weight参数穿这个值，不要用 class_weight 这个参数，在keras的_make_class_weight_map_fn函数里，class_weight接受的是字典对象。 https://stackoverflow.com/questions/62913700/valueerror-the-truth-value-of-an-array-with-more-than-one-element-is-ambiguous

好兄弟，这问题至少都可以解决，我想知道最关键的，他的源码里面没有获取code_gadget的代码，怎么从源代码提取code_gadget的方法并没有，复现出来的结果没办法用在新数据集中，好头疼啊。您那边有这个提取code_gadget的方法吗？