jetson-inference
jetson-inference copied to clipboard
following your instructions for collecting my own object detection models doesn't work
2022-02-07 08:30:40 - Using CUDA...
2022-02-07 08:30:40 - Namespace(balance_data=False, base_net=None, base_net_lr=0.001, batch_size=4, checkpoint_folder='models/Cosmetics', dataset_type='voc', datasets=['data/Cosmetics'], debug_steps=10, extra_layers_lr=None, freeze_base_net=False, freeze_net=False, gamma=0.1, lr=0.01, mb2_width_mult=1.0, milestones='80,100', momentum=0.9, net='mb1-ssd', num_epochs=100, num_workers=2, pretrained_ssd='models/mobilenet-v1-ssd-mp-0_675.pth', resume=None, scheduler='cosine', t_max=100, use_cuda=True, validation_epochs=1, weight_decay=0.0005)
2022-02-07 08:30:40 - Prepare training datasets.
Traceback (most recent call last):
File "train_ssd.py", line 214, in
Why am I getting these errors, I spent hours taking pictures for horrible results The only difference I did was not to press the merge button I wanted to learn the regular way
Please help me ASAP I have spent countless hours trying to figure out what the problem is and there is no information on github or nvidia to help me labels.txt
2022-02-07 08:30:40 - Using CUDA... 2022-02-07 08:30:40 - Namespace(balance_data=False, base_net=None, base_net_lr=0.001, batch_size=4, checkpoint_folder='models/Cosmetics', dataset_type='voc', datasets=['data/Cosmetics'], debug_steps=10, extra_layers_lr=None, freeze_base_net=False, freeze_net=False, gamma=0.1, lr=0.01, mb2_width_mult=1.0, milestones='80,100', momentum=0.9, net='mb1-ssd', num_epochs=100, num_workers=2, pretrained_ssd='models/mobilenet-v1-ssd-mp-0_675.pth', resume=None, scheduler='cosine', t_max=100, use_cuda=True, validation_epochs=1, weight_decay=0.0005) 2022-02-07 08:30:40 - Prepare training datasets. Traceback (most recent call last): File "train_ssd.py", line 214, in target_transform=target_transform) File "/jetson-inference/python/training/detection/ssd/vision/datasets/voc_dataset.py", line 36, in init self.ids = self._read_image_ids(image_sets_file) File "/jetson-inference/python/training/detection/ssd/vision/datasets/voc_dataset.py", line 111, in _read_image_ids if self._get_num_annotations(image_id) > 0: File "/jetson-inference/python/training/detection/ssd/vision/datasets/voc_dataset.py", line 123, in _get_num_annotations objects = ET.parse(annotation_file).findall("object") File "/usr/lib/python3.6/xml/etree/ElementTree.py", line 1196, in parse tree.parse(source, parser) File "/usr/lib/python3.6/xml/etree/ElementTree.py", line 586, in parse source = open(source, "rb") ValueError: embedded null byte
Why am I getting these errors, I spent hours taking pictures for horrible results The only difference I did was not to press the merge button I wanted to learn the regular way
Please help me ASAP I have spent countless hours trying to figure out what the problem is and there is no information on github or nvidia to help me labels.txt
I highly respect you and I know you will get me out of this with the help I need
You should go to https://github.com/qfgaohao/pytorch-ssd which is where the training code is branched from and see if someone had a similar error
thank you very much I hope dusty gets back to me soon please and thank you
File "/usr/lib/python3.6/xml/etree/ElementTree.py", line 586, in parse source = open(source, "rb") ValueError: embedded null byte
Hi @Gianni2045, it appears that one of your XML files is corrupted. To find out which, first uncomment this line of code from jetson-inference/python/training/ssd/vision/datasets/voc_dataset.py
(line 76)
https://github.com/dusty-nv/pytorch-ssd/blob/8ed842a408f8c4a8812f430cf8063e0b93a56803/vision/datasets/voc_dataset.py#L76
If you are running the container, you need to make this change inside the container (i.e. using nano
text editor)
Then run train_ssd.py with these command-line flags included: --batch-size=1 --workers=1 --debug-steps=1
It will then print out info about the XML/image files as it loads them. The last one loaded before the exception occurs is the problem, so remove the corresponding entry from your ImageSet files.
You can also just send me your dataset on Google Drive or somewhere and I will try it out.
thank you sir you are an admirable worker
thank you very much you truly are the best teacher I ever had
No problem @Gianni2045, happy to help :)
Hope you get it working, if not let me know.
please forgive my ignorance i try my best not to be but I have been trying to send you my information attaching my files here it wont accept that type of file, how do I please send you the data in google drive?
I think I figured it out how to share my data thank you so much for your care as a teacher
hope i will understand your feedback on this shared data
I sent you the data please with all respect lete know what information of problems you found in my data Dusty
Thank you again for being an amazing teacher
Hi @Gianni2045 @GianniM2045, I'm having trouble downloading all the individual folders you sent me on Google Drive. Can you compress your entire dataset into a single .zip or .tar.gz archive and send me that on google drive instead? Thanks.
Yes I will try
On Mon, Feb 14, 2022, 12:05 PM Dustin Franklin @.***> wrote:
Hi @Gianni2045 https://github.com/Gianni2045 @GianniM2045 https://github.com/GianniM2045, I'm having trouble downloading all the individual folders you sent me on Google Drive. Can you compress your entire dataset into a single .zip or .tar.gz archive and send me that on google drive instead? Thanks.
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#issuecomment-1039390789, or unsubscribe https://github.com/notifications/unsubscribe-auth/AORU47FX4JFWFG43JKGX5M3U3E75BANCNFSM5NWYQXUA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you were mentioned.Message ID: @.***>
thank you for your support here is my zip file
20220208-022651.zip https://drive.google.com/file/d/1QaMNDQ-UAQogwbqAomApEzW1D6OlN2V_/view?usp=drive_web
Message ID: @.***>
https://drive.google.com/file/d/1QaMNDQ-UAQogwbqAomApEzW1D6OlN2V_/view?usp=drive_web
Hi @GianniM2045, is this the link? I've requested access to download it.
suddes.zip https://drive.google.com/file/d/1tgTWfsq-xUyL2iNOywVysq4vb2Et66o9/view?usp=drive_web
El lun, 14 feb 2022 a la(s) 15:07, Jorge Morales @.***) escribió:
Yes I will try
On Mon, Feb 14, 2022, 12:05 PM Dustin Franklin @.***> wrote:
Hi @Gianni2045 https://github.com/Gianni2045 @GianniM2045 https://github.com/GianniM2045, I'm having trouble downloading all the individual folders you sent me on Google Drive. Can you compress your entire dataset into a single .zip or .tar.gz archive and send me that on google drive instead? Thanks.
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#issuecomment-1039390789, or unsubscribe https://github.com/notifications/unsubscribe-auth/AORU47FX4JFWFG43JKGX5M3U3E75BANCNFSM5NWYQXUA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you were mentioned.Message ID: @.***>
yes this is the link and this one also
El mar, 15 feb 2022 a la(s) 10:25, Jorge Morales @.***) escribió:
suddes.zip https://drive.google.com/file/d/1tgTWfsq-xUyL2iNOywVysq4vb2Et66o9/view?usp=drive_web
El lun, 14 feb 2022 a la(s) 15:07, Jorge Morales ( @.***) escribió:
Yes I will try
On Mon, Feb 14, 2022, 12:05 PM Dustin Franklin @.***> wrote:
Hi @Gianni2045 https://github.com/Gianni2045 @GianniM2045 https://github.com/GianniM2045, I'm having trouble downloading all the individual folders you sent me on Google Drive. Can you compress your entire dataset into a single .zip or .tar.gz archive and send me that on google drive instead? Thanks.
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#issuecomment-1039390789, or unsubscribe https://github.com/notifications/unsubscribe-auth/AORU47FX4JFWFG43JKGX5M3U3E75BANCNFSM5NWYQXUA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you were mentioned.Message ID: @.***>
thank you very much
El mar, 15 feb 2022 a la(s) 10:27, Jorge Morales @.***) escribió:
yes this is the link and this one also
El mar, 15 feb 2022 a la(s) 10:25, Jorge Morales ( @.***) escribió:
suddes.zip https://drive.google.com/file/d/1tgTWfsq-xUyL2iNOywVysq4vb2Et66o9/view?usp=drive_web
El lun, 14 feb 2022 a la(s) 15:07, Jorge Morales ( @.***) escribió:
Yes I will try
On Mon, Feb 14, 2022, 12:05 PM Dustin Franklin @.***> wrote:
Hi @Gianni2045 https://github.com/Gianni2045 @GianniM2045 https://github.com/GianniM2045, I'm having trouble downloading all the individual folders you sent me on Google Drive. Can you compress your entire dataset into a single .zip or .tar.gz archive and send me that on google drive instead? Thanks.
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#issuecomment-1039390789, or unsubscribe https://github.com/notifications/unsubscribe-auth/AORU47FX4JFWFG43JKGX5M3U3E75BANCNFSM5NWYQXUA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you were mentioned.Message ID: @.***>
suddes.zip https://drive.google.com/file/d/1tgTWfsq-xUyL2iNOywVysq4vb2Et66o9/view?usp=drive_web
OK, I requested access to this one also
I accepted your request thank you so much for your help
On Tue, Feb 15, 2022, 10:36 AM Dustin Franklin @.***> wrote:
suddes.zip https://drive.google.com/file/d/1tgTWfsq-xUyL2iNOywVysq4vb2Et66o9/view?usp=drive_web
OK, I requested access to this one also
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#issuecomment-1040495355, or unsubscribe https://github.com/notifications/unsubscribe-auth/ATVZXRLJGYEZ7NSLO4EHORLU3J6HJANCNFSM5NWYQXUA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you were mentioned.Message ID: @.***>
Thank you so much for completing my submission
On Thu, Apr 27, 2023, 11:56 AM Dustin Franklin @.***> wrote:
Closed #1353 https://github.com/dusty-nv/jetson-inference/issues/1353 as completed.
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#event-9116898688, or unsubscribe https://github.com/notifications/unsubscribe-auth/AORU47BWKD2LM5BCPJV6YUTXDKQKXANCNFSM5NWYQXUA . You are receiving this because you were mentioned.Message ID: @.***>
Hope you are doing well dusty, Jesus bless you always.
On Thu, Apr 27, 2023, 12:40 PM Jürgen Morales Rizzo Vagner < @.***> wrote:
Thank you so much for completing my submission
On Thu, Apr 27, 2023, 11:56 AM Dustin Franklin @.***> wrote:
Closed #1353 https://github.com/dusty-nv/jetson-inference/issues/1353 as completed.
— Reply to this email directly, view it on GitHub https://github.com/dusty-nv/jetson-inference/issues/1353#event-9116898688, or unsubscribe https://github.com/notifications/unsubscribe-auth/AORU47BWKD2LM5BCPJV6YUTXDKQKXANCNFSM5NWYQXUA . You are receiving this because you were mentioned.Message ID: @.***>