Open Dangxc opened 1 year ago
I executed "mnist_direct.py" as well as "mnist_generative.py" but it just created result of that mentioned paper not the csv file can you find a way to do it?
do you have p_data.csv file?
I got error at following line of code "def poi_data(poison_rate): poison_number = int(poison_rate * 50000) poisoned_x_data = np.load("pdata%d.npy"%(poison_number)). <----- poisoned_y_data = np.load("plabel%d.npy"%(poison_number))". <-------
For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:
“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."
But I can’t save them in 'npy' format, could you get it follow the way from the author?
I will try and tell you as soon as possible can we connect on LinkedIn for easy communication? https://www.linkedin.com/in/meeet
Regards Meet Patel On Sat, Apr 15, 2023, 11:34 AM Dangxc @.***> wrote:
For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:
“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."
But I can’t save them in 'npy' format, could you get it follow the way from the author?
— Reply to this email directly, view it on GitHub https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1509556289, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOVVA3OJKMZTMUDUPV6SY2TXBI25JANCNFSM6AAAAAAWQHGWVM . You are receiving this because you commented.Message ID: <chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1509556289 @github.com>
I'm sorry I don't have linkedin account, we can contact through email, I have sent an email to your gmail, please pay attention to check your Google email.
Xiaocui Dang | |
---|---|
@. | ---- Replied Message ---- | From | Meet @.> | | Date | 4/15/2023 17:54 | | To | @.> | | Cc | @.> , @.***> | | Subject | Re: [chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks] Can not find the file "p_labels.csv" (Issue #1) |
I will try and tell you as soon as possible can we connect on LinkedIn for easy communication? https://www.linkedin.com/in/meeet
Regards Meet Patel On Sat, Apr 15, 2023, 11:34 AM Dangxc @.***> wrote:
For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:
“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."
But I can’t save them in 'npy' format, could you get it follow the way from the author?
— Reply to this email directly, view it on GitHub https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1509556289, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOVVA3OJKMZTMUDUPV6SY2TXBI25JANCNFSM6AAAAAAWQHGWVM . You are receiving this because you commented.Message ID: <chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1509556289 @github.com>
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Hello, here is the code that help me to create the file while executing the code and saving it with .npy format. python code is "np.save('p_data_15000.npy', data_p.asnumpy()) " and same for label file.
Regards, Meet
On Mon, Apr 17, 2023 at 8:11 AM Dangxc @.***> wrote:
I'm sorry I don't have linkedin account, we can contact through email, I have sent an email to your gmail, please pay attention to check your Google email.
Xiaocui Dang @. | ---- Replied Message ---- | From | Meet @.> | | Date | 4/15/2023 17:54 | | To | @.> | | Cc | @.> , @.***> | | Subject | Re: [chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks] Can not find the file "p_labels.csv" (Issue #1) |
I will try and tell you as soon as possible can we connect on LinkedIn for easy communication? https://www.linkedin.com/in/meeet
Regards Meet Patel On Sat, Apr 15, 2023, 11:34 AM Dangxc @.***> wrote:
For the p_data.csv and p_labels.csv, I have contacted the author, he gave me a reply:
“You can run mnist_direct.py and obtain the generate poisoned data directly. For instance, in line 151 of mnist_direct.py, the method begins to generate poisoned data and the variable 'data_p' and 'label_p 're the final poisoned data and the corresponding label. After obtaining the poisoned data and the label, you can save them in "npy" format."
But I can’t save them in 'npy' format, could you get it follow the way from the author?
— Reply to this email directly, view it on GitHub < https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1509556289 , or unsubscribe < https://github.com/notifications/unsubscribe-auth/AOVVA3OJKMZTMUDUPV6SY2TXBI25JANCNFSM6AAAAAAWQHGWVM
. You are receiving this because you commented.Message ID:
<chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1509556289 @github.com>
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
— Reply to this email directly, view it on GitHub https://github.com/chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1#issuecomment-1510607817, or unsubscribe https://github.com/notifications/unsubscribe-auth/AOVVA3LM3GDT2VHVIZRUY4DXBSUT7ANCNFSM6AAAAAAWQHGWVM . You are receiving this because you commented.Message ID: <chetanniloor/De-pois-An-Attack-Agnostic-Defense-against-Data-Poisoning-Attacks/issues/1/1510607817 @github.com>
OSError: p_labels.csv not found. And how to generate the file “p_labels.csv‘’?