gustavz / deeptraining_hands Goto Github PK
View Code? Open in Web Editor NEWDataset, necessary Scripts and trained SSD Model for detecting Hands in Realtime.
Dataset, necessary Scripts and trained SSD Model for detecting Hands in Realtime.
Hey when I ran mat_to_xml.py I got this error:
mona@Mona:~/code/handpose/deeptraining_hands$ python mat_to_xml.py
successfully converted {}-labels from mat to pascal-xml
Traceback (most recent call last):
File "mat_to_xml.py", line 213, in <module>
main()
File "mat_to_xml.py", line 209, in main
print ("successfully converted {}-labels from mat to pascal-xml").format(directory)
AttributeError: 'NoneType' object has no attribute 'format'
how should this be fixed?
I get the following error when setting up for egohands. Can you please share the fix?
4795 egohands/_LABELLED_SAMPLES/CHESS_OFFICE_T_H_frame_2669.jpg
4796 egohands/_LABELLED_SAMPLES/CHESS_OFFICE_T_H_frame_2186.jpg
4797 egohands/_LABELLED_SAMPLES/CHESS_OFFICE_T_H_frame_1563.jpg
4798 egohands/_LABELLED_SAMPLES/CHESS_OFFICE_T_H_frame_0262.jpg
4799 egohands/_LABELLED_SAMPLES/CHESS_OFFICE_T_H_frame_1768.jpg
4800 egohands/_LABELLED_SAMPLES/CHESS_OFFICE_T_H_frame_1332.jpg
> done scanning director CHESS_OFFICE_T_H
Train/Eval content generation complete!
Traceback (most recent call last):
File "egohands_setup.py", line 272, in <module>
main()
File "egohands_setup.py", line 266, in main
download_egohands_dataset(EGOHANDS_DATASET_URL, EGO_HANDS_FILE)
File "egohands_setup.py", line 236, in download_egohands_dataset
extract_folder(dataset_path)
File "egohands_setup.py", line 219, in extract_folder
rename_files("egohands/_LABELLED_SAMPLES/")
File "egohands_setup.py", line 210, in rename_files
generate_csv_files("egohands/_LABELLED_SAMPLES/")
File "egohands_setup.py", line 191, in generate_csv_files
split_data_test_eval_train("egohands/_LABELLED_SAMPLES/")
File "egohands_setup.py", line 182, in split_data_test_eval_train
generate_label_files("data/")
File "egohands_setup.py", line 129, in generate_label_files
if(f.split(".")[1] == "csv"):
IndexError: list index out of range
In ssd config file I found this line.
"deeptraining_hands/model/ssd_handsnet_checkpoints/model.ckpt-..."
So, is it do you means "ssd_mobilenet_checkpoints" folder in your repo?
Hi, thank you for sharing.
I run into this problem when executing the oxfordhands_setup.py
:
`
equal directory sizes, everything ok!
Buffy_225.jpg already exists
renaming to xBuffy_225.jpg!
Traceback (most recent call last):
File "oxfordhand_dataset_setup.py", line 112, in
main()
File "oxfordhand_dataset_setup.py", line 107, in main
cleanup_structure(data_path, dataset_path, tarfile_path)
File "oxfordhand_dataset_setup.py", line 86, in cleanup_structure
sh.copyfile(src_dir+file, drc_dir+newfile)
TypeError: must be str, not NoneType
`
Do you have any suggestion to resolve this problem?
./darknet detector train /path/to/model.data path/to/model.cfg path/to/weights
In here, which value weights can I use to train YOLO for hand (darknet19_448.conv.23 or yolov3-tiny.weights)?
How can I compare the result of SSD and YOLO with mAP metric in hand object detection?
How can I get mAP value of these two models?
I am interested up till converting xml to csv but I am getting errors regarding pathing.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.