Deep-Packet
Deep-Packet copied to clipboard
munhouiani
training fails on VPN dataset with a ValueError
I see a ValueError: Please pass features or at least one example when writing data` at the end of train_cnn when run on VPN dataset. I have not modified the code. I faced NaN error and set under sampling to False. Then I encountered this one.
Here is the detailed output ``Trainer(val_check_interval=1.0)` was configured so validation will run at the end of the training epoch..
| Name | Type | Params
0 | conv1 | Sequential | 1.0 K 1 | conv2 | Sequential | 200 K 2 | max_pool | MaxPool1d | 0 3 | fc1 | Sequential | 9.9 M 4 | fc2 | Sequential | 20.1 K 5 | fc3 | Sequential | 5.0 K 6 | out | Linear | 867
10.1 M Trainable params
0 Non-trainable params
10.1 M Total params
40.430 Total estimated model params size (MB)
Using custom data configuration train.parquet-2c3be5e9d214c057
Downloading and preparing dataset parquet/train.parquet to /home/rvn/.cache/huggingface/datasets/parquet/train.parquet-2c3be5e9d214c057/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec...
Downloading data files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 3663.15it/s]
Extracting data files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 565.27it/s]
Traceback (most recent call last):
File "/home/rvn/Deep-Packet/train_cnn.py", line 33, in features or at least one example when writing data")
ValueError: Please pass features or at least one example when writing data`
I faced NaN error and set under sampling to False. You dont need to set False. Under sampling is quiet an important process. Try to correct the processed_data ,open one of the .json file,check the app_label and traffic_label,if value is null that means u should add the specific prefix-id according to your dataset in utlis.py. PREFIX_TO_APP_ID = { # AIM chat "aim_chat_3a": 0, "aim_chat_3b": 0, "aimchat1": 0, "aimchat2": 0, "vpn_aim_chat1a":0, "vpn_aim_chat1b":0, # Email "email1a": 1, "email1b": 1, "email2a": 1, "email2b": 1, "vpn_email2a": 1, "vpn_email2b": 1, # Facebook "facebook_audio1a": 2, "facebook_audio1b": 2, "facebook_audio2a": 2, "facebook_audio2b": 2, "facebook_audio3": 2, "facebook_audio4": 2, "facebook_chat_4a": 2, "facebook_chat_4b": 2, "facebook_video1a": 2, "facebook_video1b": 2, "facebook_video2a": 2, "facebook_video2b": 2, "facebookchat1": 2, "facebookchat2": 2, "facebookchat3": 2, "vpn_facebook_audio2":2, "vpn_facebook_chat1a":2, "vpn_facebook_chat1b":2, # FTPS "ftps_down_1a": 3, "ftps_down_1b": 3, "ftps_up_2a": 3, "ftps_up_2b": 3, "vpn_ftps_A":3, "vpn_ftps_B":3, # Gmail "gmailchat1": 4, "gmailchat2": 4, "gmailchat3": 4, # Hangouts "hangout_chat_4b": 5, "hangouts_audio1a": 5, "hangouts_audio1b": 5, "hangouts_audio2a": 5, "hangouts_audio2b": 5, "hangouts_audio3": 5, "hangouts_audio4": 5, "hangouts_chat_4a": 5, "hangouts_video1b": 5, "hangouts_video2a": 5, "hangouts_video2b": 5, "vpn_hangouts_audio1":5, "vpn_hangouts_audio2":5, "vpn_hangouts_chat1a":5, "vpn_hangouts_chat1b":5, # ICQ "icq_chat_3a": 6, "icq_chat_3b": 6, "icqchat1": 6, "icqchat2": 6, # Netflix "netflix1": 7, "netflix2": 7, "netflix3": 7, "netflix4": 7, # SCP "scp1": 8, "scpdown1": 8, "scpdown2": 8, "scpdown3": 8, "scpdown4": 8, "scpdown5": 8, "scpdown6": 8, "scpup1": 8, "scpup2": 8, "scpup3": 8, "scpup5": 8, "scpup6": 8, # SFTP "sftp1": 9, "sftp_down_3a": 9, "sftp_down_3b": 9, "sftp_up_2a": 9, "sftp_up_2b": 9, "sftpdown1": 9, "sftpdown2": 9, "sftpup1": 9, # Skype "skype_audio1a": 10, "skype_audio1b": 10, "skype_audio2a": 10, "skype_audio2b": 10, "skype_audio3": 10, "skype_audio4": 10, "skype_chat1a": 10, "skype_chat1b": 10, "skype_file1": 10, "skype_file2": 10, "skype_file3": 10, "skype_file4": 10, "skype_file5": 10, "skype_file6": 10, "skype_file7": 10, "skype_file8": 10, "skype_video1a": 10, "skype_video1b": 10, "skype_video2a": 10, "skype_video2b": 10, # Spotify "spotify1": 11, "spotify2": 11, "spotify3": 11, "spotify4": 11, # Vimeo "vimeo1": 12, "vimeo2": 12, "vimeo3": 12, "vimeo4": 12, # Voipbuster "voipbuster1b": 13, "voipbuster2b": 13, "voipbuster3b": 13, "voipbuster_4a": 13, "voipbuster_4b": 13, # Youtube "youtube1": 14, "youtube2": 14, "youtube3": 14, "youtube4": 14, "youtube5": 14, "youtube6": 14, "youtubehtml5_1": 14, #bittorrent "vpn_bittorrent":15, } The dataset i use is VPN-PCAPS-01.
