Sign Language Detection Using Machine Learning | Python Project
HTML-код
- Опубликовано: 29 сен 2022
- Sign Language Detection Using Machine Learning | Python Project
==============================================
Project Code: -
github.com/kumarvivek9088/Sig...
Data Images which I captured in this Video to train Model :-
drive.google.com/drive/folder...
Data for all the Alphabets: -
drive.google.com/drive/folder...
==============================================
Like Share Comment
And Subscribe
![NoCap - Yacht Party [Official Music Video]](http://i.ytimg.com/vi/rm_lvDln8kE/mqdefault.jpg)
how did you get the code,do you programmed it yourself or from any other sources...However this is amazing...keep it up...never give up...dont think of the number of subscribers bro...just go on...one day day you will become succesfull
abe chal
Thank u so much for guiding in a clear way...
Thank you so much brother. You don't know how important this video is to me. May God bless you
kyu ni horhi padhai
I was struggling since 2 weeks for sign language detection and finally i found ur video !!! Thankkkkk youuuu sooooo muchhhhhh ... I finally executed itttttt and i am sooooo happppyyyyyyyy
bro that A is not working for me
@@HarshYadav-tj5qb mine also
could you pls explain how you execute it
chaatna bandh kar uski
Did you really got the output
Thanks you really helped me
thank you for making this video
👍👍
Bro you just saved me
Love you brother ❤
Good
THANK YOU SO MUCH ...
thankyou bhai
thankssss a lott. worked like a butter
nice vivek
en ke time ye dekh rha hu me
shukriya bhai
I am getting this error while running the model file"data = np.asarray(data_dict['data'])
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (41293,) + inhomogeneous part." what should I do for resolving this error.. please help me
I have the same error please help to solve it
Hey man
I used your MP_Data file to train the model but it is giving random output any solution?
It also takes a lot of time to change if we show a new sign
Bro you are an angel ❤❤
I just wanna ask, how did you get the accuracy of your sign language?
I got this error when i train the model . can you pls help me . Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated, ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray).
Did u solved it..! Me also facing the same prblm if u solve it please help tommarrow I have presentation
I trained my model for all letters, even got the MP_Data correctly, but on training the model it gives errors,
Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated, ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray).
Can you please help with this
same
same bro . are you solved it?
@@kausikar2574 Yes I was able to solve it, the issue was basically some images were not captured correctly so their np data was not created, the error means that since there are some missing data for some images, so what I did, I printed the dimensions of all the images to see which images were not captured properly, and I replaced them
how u didthis cAN U PLEASE SHARE the code of it i face same error
@@aryankarkra6848
If you did a project on this could you please share the report?
when i train the model i get an error :-
raise ValueError("Object arrays cannot be loaded when"
ValueError: Object arrays cannot be loaded whenallow_pickle=True
can you please help me solve this error
same
same, were you able to solve this?
Same error I'm facing
Same error if you found the solution please let us know
can you help me this is not working on my pc every modules are installed stated in the requiremnets.txt file
This error is coming when I try to install Mediapipe
Defaulting to user installation because normal site-packages is not writeable
ERROR: Could not find a version that satisfies the requirement mediapipe (from versions: none)
ERROR: No matching distribution found for mediapipe
why is this happening? I have tried to reinstall py
WHAT ARE THE VERSIONS OF LIBRARIES
I MEAN TENSORFLOW,MATPLOT,KERAS ETC...
Can you please help me with the other letters, I'm getting error when u said to add in array.
Help please
Which package u installed
may I know which method is used, like CNN or what
Brother images save ni ho rhi particular folder m
CAN YOU PLEASE PROVIDE THE CAPTURED DATA FOR OTHER ALPHABETS AS WELL. IT WILL BE VERY HELPFUL TO US
Check description box
Which model does it work on
Even after collecting data for other alphabets while predicting it is not working , only alphabet A is detected
9:05 erorr plz help
line 2, in
from sklearn.model_selection import train_test_split
ModuleNotFoundError: No module named 'sklearn'
install sklearn model if you are getting this error , pip install scikit-learn
@@ProgresswithPython sir is it necessary that I should take images from that program, what if i clicked images from external camera and put those in folder
Why is there errors coming when I try to train those models for all alphabets?
Is there any changes required in code?
depends upon your dataset, In this video i have used dataset of 15 so I put 15 in required places in the code as mentioned in video, if your dataset is larger or smaller than 15 than you have to do changes in code
in
import mediapipe as mp
ModuleNotFoundError: No module named 'mediapipe'
how to resolve this error
did you install mediapipe module?
I'm unable to add other letters from D, please help! It is showing an error in datatrain.py file
while using the final code my camera is not opening pls suggest some solution. All other codes that access the camera feed works perfectly fine
how to train data for other albhabets ?
how to create dataset or image of J and Z letter?
Traceback (most recent call last):
File "e:\HandSignDetection\collectdata.py", line 2, in
import cv2
ModuleNotFoundError: No module named 'cv2'
this error is showing what to do?
did you install opencv?
change python version 3.11.2 to 3.10.7
bhai thora detail vedio bana do pls
Bro what changes to do for all alphabets kindly share. Asap
Hi bro when i press a in key board images are not saving in folder why it is happening
You have to press small letters not capital letters
Bhai ek video how to convert sign language to text to voice please 🥺🙏
While executing the code its showing only a,b,c for every sign we made i download alpahbets folder from your description but nthing changes
You have to train your model from that dataset
@@ProgresswithPython i did that, i added images and functions of other letters but while executing it it detects only a,b,c letters only
@@vamsianurag3415 did you train model for other alphabets?
how to capture the images?
My data.py file is running but there is no output shown.what should I do
is there any error showing ?
sir please help main aahe ke sign language ka data capture kiya lekin jab main train module karne gaya to vo module only a,b,c ke train hua baki ke liya nahi ho raha hai ...........
you have update action list present in function.py file, you have to update action list with all alphabet
I executed the data collection code but the data is not being captured even after pressing the alphabet n number of times. Can you help me with this issue
make sure you pressing letter without caps lock on
@@ProgresswithPythonthank you
which python version you were using? Latest version dose not support mediapipe !
Python 3.10.7
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (780, 30) + inhomogeneous part.
what to do now help me to solve this prb
Same error
how to convert this into apk.
needed sudden replay
Bro my model is not getting trained can you please explain it
I have this error how to sove this error FileNotFoundError: [Errno 2] No such file or directory: 'model. ison"
Write the correct name and location of the saved model
I'm not able to install the tensorflow ...could you please help me with how to install the tensorflow and the rest
what error it is showing?
How you got MP DATA CAN SOMEBODY PLEASE TELL MEE
Bhai Aapne Jo Sign Language Detection ka Project banaya hai pls iska Project Report ka bhi link de dijiye.
Which algorithm do you use?
Lstm
which version of python should we use for this code to run without any error
Python 3.10.7
Thanks for the video! How to add another alphabet to the detector?
train your model for other alphabet also
@@ProgresswithPython how to train?
any reference
?
what is sklearn
While executing it's showing error
ModuleNotFoundError: No module named 'sklearn'
sklearn module is not install in ur sys so for that install the module ....type this command pip install sklearn.model_selection
awesome video.. Bro how we can store image in mysql and retrieve in django please help me ...Iam using BLOB but it is not working!!!!
save the path and retrieve it using script
Your data set can't be upload
Bro i have an error system cannot find the path specified:'Image//A'
you need to create a new folder called 'Image' in the same repository
FileNotFoundError: [Errno 2] No such file or directory: 'model.json' | me getting this error
check your model.json is created or not in your code directory.
@@ProgresswithPython Traceback (most recent call last):
File "c:\Users\hp\Downloads\SLD\SignLanguageDetectionUsingML-main\data.py", line 33, in
image, results = mediapipe_detection(frame, hands)
File "c:\Users\hp\Downloads\SLD\SignLanguageDetectionUsingML-main\function.py", line 11, in mediapipe_detection
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # COLOR CONVERSION BGR 2 RGB
cv2.error: OpenCV(4.6.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'
I would appreciate ENGLISH videos
how to combine alphabet to form a word
how to store language such as hello , food ,yes or no because I want it to give sentence also
This comes under action recognition which can be done by using this lstm algo but it can't be possible to explain here how to implement this. This require a detailed video on it
@@ProgresswithPython i tried to use like , hello and other things instead of A and B and the images and dataset get captured perfectly but when I train model then it gives error numpy array can't convert in ternsorflow object
mera train model wala code mai error show nhi horaha but run bhi nhi horaha
could you help me with python version for this project?? and can you provide the github link of project for all the signs which you have implemented (A-Z).
Check description box
python 3.10
If you did this project, could you please share the report?
I have trained model for A B C but it is not showing accurate results if I do sign of B it is showing C. And along some message is also coming
And with it a VisibleDeprecationWarnig also coming.
Please tell me what changes i have to do in code if I want to add all alphabets in the data set
you have to change only array where you have to write all alphabet. array name is "actions" present in function.py
What about Data set ? Can you Send me The Dataset of all alphabets Bcz my webcam quality isn't good enough
I provided a link in description , so you can directly train your model for all alphabet
@@ProgresswithPython No such file or directory: 'MP_Data\\D\\0\\15.npy' getting this error while training the model
@@Sahil-xs7nd how did u solved this error?
its showing an error
NotADirectoryError: [WinError 267] The directory name is invalid: 'Image//A'
pls help i have to do mine presentation
You have to create data first
@@ProgresswithPython ok
pip install tensorflow
ERROR: Could not find a version that satisfies the requirement tensorflow (from versions: none)
ERROR: No matching distribution found for tensorflow
This error is coming how to fix this issue anyone?
Try to use python 3.10 version because some modules is not installing in latest one
@@ProgresswithPython thanku it's resolved
How to change the text value sir or the response example if i want the response to be words
Sorry I didn't understand, can you explain it what changes you want.
@@ProgresswithPython he wants to say that what If i want output in the form of phrase like "hello guys welcome" etc not just ABCD
@@daddyyyyyyyyyyyy yes we can do that using this lstm algo and for this we have to write a fresh code.
@@ProgresswithPython I am doing this project now and I don't know how to create words , can u please tell where to change code
@@vibhacreation6698 I have to make a separate video for this.
can we use two handed gestures ???
Yes we can ,but we have to do some changes in code
@@ProgresswithPython what changes pls make video
Please share your linkedin profile or something where we could connect
You can msg me on Instagram, instagram.com/progresswithpython
can you detect more than 3 alphabets?
if yes what would be changes in code?
yes, for that you have to create data for all alphabet
@@ProgresswithPython is there updated code?
@@ProgresswithPython when i add more data the model gives wrong output/less accuracy do uk why it happens
@@labhjoshi3182 try to train with more no. of dataset.
My program is running but Im unable to get the camera for capturing Plzzz help
Any errors
pip install tensorflow is not working in my cmd
Make sure your Python is installed properly
Data collect successfully, but when i train the model it doesn't work and did not show accuracy
is there any error occurred?
@@ProgresswithPython No , 0 error
Which library package u installed
Tensorflow and mediapipe
row = frame.shape[1]
^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'shape'
i got error on this line could you plz help me bro......
Multiple errors in app.py like cv2 not defined.
What will be the minimum PC specs required?
Just need a good quality camera with your pc and having python in it.
@@ProgresswithPython will it work on 8 gb ram ? I made one myself but its taking a lot or ram to run so I wanted to work on something which is optimised.
@@frost0091 it work well in 8 gb ram, mine have also 8gb ram in my pc
@@ProgresswithPython Okay thanks
@@ProgresswithPython Do you have any source from where i can read about these things you used in this project
Traceback (most recent call last):
File "c:\Users\Mailt\OneDrive\Desktop\sign_detect\trainmodel.py", line 14, in
res = np.load(os.path.join(DATA_PATH, action, str(sequence), "{}.npy".format(frame_num)))
File "C:\Users\Mailt\AppData\Local\Programs\Python\Python310\lib\site-packages
umpy\lib
pyio.py", line 438, in load
raise ValueError("Cannot load file containing pickled data "
ValueError: Cannot load file containing pickled data when allow_pickle=False
PS C:\Users\Mailt\OneDrive\Desktop\sign_detect>
You have issues with your data set , may be due to blur images. You can find that images and replace with good ones.
Did you solved this error?
@Khushi Sharma this error coming due to your dataset as your dataset is not proper , you have to make it again
i am getting same error ..if any have solved please let me know
@CHERUKU SATYAVANI github.com/kumarvivek9088/data , use this data set to train model and this dataset doesn't contain data for alphabet H ,Z
it is giving me an error in data.py can you tell me how to fix it
ImportError: DLL load failed while importing _framework_bindings: The specified module could not be found.
This is the error it is giving me.
Mediapipe ka konsa version use kiye ho aar Python ka
@@raselaktarimam9723 python 3.12 hai
aur mediapipe mera latest version hai
@@raselaktarimam9723 im using VS code and mediapipe latest version
@@raselaktarimam9723 meidapiep ka latest version hai aur python mai vs code pa kar raha hun
mediapipe ka latest version and python mai vs code pa kar raha hun
Sir I have a question plz replay me
I cleared all the mistakes which were made by me...Everything is working for me..output screen came but it is not showing any alphabets with accuracy pls help me with this one its very urgent i want to submit report on this🙏🙏
You can use my dataset to train your model with all alphabets
@@ProgresswithPython bro but im going to develop a system that translates indian sign language how can i use ur dataset
@@ProgresswithPython but i tried copy pasting a indian sign language dataset from kaggle but it is showing some error it is in jpg format..... Do i have any alternate options for my issue... Say me something that i can change..by collecting the datasets from my camera itself pls bro
@@ProgresswithPython but what is the exact reason for my issue why it is not showing what alphabet i'm showing
@@kumar-dx7mzhello , Is your problem is resolve ?
bro this error am getting ,, please help
res = np.load(os.path.join(DATA_PATH, action, str(sequence), "{}.npy".format(frame_num)))
File "C:\Users\harshit\AppData\Local\Programs\Python\Python310\lib\site-packages
umpy\lib
pyio.py", line 432, in load
return format.read_array(fid, allow_pickle=allow_pickle,
File "C:\Users\harshit\AppData\Local\Programs\Python\Python310\lib\site-packages
umpy\lib\format.py", line 787, in read_array
raise ValueError("Object arrays cannot be loaded when "
ValueError: Object arrays cannot be loaded when allow_pickle=False
same mera bhi yhi dikkat aa rha hai
same error i got , were you able solve it?@@vivek_bhu
Bro i can't install tensor flow in cmd
What do bro please replay
What is your python version?
@@ProgresswithPython 10
@@ProgresswithPython it shows error exception
@@chinthangu929 can you copy paste your error here
@@ProgresswithPython ERROR: Exception:
Traceback (most recent call last):
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor\urllib3
esponse.py", line 438, in _error_catcher
yield
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor\urllib3
esponse.py", line 519, in read
data = self._fp.read(amt) if not fp_closed else b""
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor\cachecontrol\filewrapper.py", line 62, in read
data = self.__fp.read(amt)
File "C:\Program Files\Python310\lib\http\client.py", line 464, in read
s = self.fp.read(amt)
File "C:\Program Files\Python310\lib\socket.py", line 705, in readinto
return self._sock.recv_into(b)
File "C:\Program Files\Python310\lib\ssl.py", line 1273, in recv_into
return self.read(nbytes, buffer)
File "C:\Program Files\Python310\lib\ssl.py", line 1129, in read
return self._sslobj.read(len, buffer)
TimeoutError: The read operation timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\cli\base_command.py", line 173, in _main
status = self.run(options, args)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\cli
eq_command.py", line 203, in wrapper
return func(self, options, args)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\commands\install.py", line 315, in run
requirement_set = resolver.resolve(
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib
esolver.py", line 94, in resolve
result = self._result = resolver.resolve(
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 472, in resolve
state = resolution.resolve(requirements, max_rounds=max_rounds)
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 366, in resolve
failure_causes = self._attempt_to_pin_criterion(name)
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 212, in _attempt_to_pin_criterion
criteria = self._get_updated_criteria(candidate)
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 203, in _get_updated_criteria
self._add_to_criteria(criteria, requirement, parent=candidate)
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor
esolvelib
esolvers.py", line 172, in _add_to_criteria
if not criterion.candidates:
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor
esolvelib\structs.py", line 151, in __bool__
return bool(self._sequence)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\found_candidates.py", line 140, in __bool__
return any(self)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\found_candidates.py", line 128, in
return (c for c in iterator if id(c) not in self._incompatible_ids)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\found_candidates.py", line 32, in _iter_built
candidate = func()
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\factory.py", line 204, in _make_candidate_from_link
self._link_candidate_cache[link] = LinkCandidate(
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 295, in __init__
super().__init__(
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 156, in __init__
self.dist = self._prepare()
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 227, in _prepare
dist = self._prepare_distribution()
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
esolution
esolvelib\candidates.py", line 305, in _prepare_distribution
return self._factory.preparer.prepare_linked_requirement(
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\operations\prepare.py", line 508, in prepare_linked_requirement
return self._prepare_linked_requirement(req, parallel_builds)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\operations\prepare.py", line 550, in _prepare_linked_requirement
local_file = unpack_url(
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\operations\prepare.py", line 239, in unpack_url
file = get_http_url(
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\operations\prepare.py", line 102, in get_http_url
from_path, content_type = download(link, temp_dir.path)
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
etwork\download.py", line 145, in __call__
for chunk in chunks:
File "C:\Program Files\Python310\lib\site-packages\pip\_internal\cli\progress_bars.py", line 144, in iter
for x in it:
File "C:\Program Files\Python310\lib\site-packages\pip\_internal
etwork\utils.py", line 63, in response_chunks
for chunk in response.raw.stream(
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor\urllib3
esponse.py", line 576, in stream
data = self.read(amt=amt, decode_content=decode_content)
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor\urllib3
esponse.py", line 512, in read
with self._error_catcher():
File "C:\Program Files\Python310\lib\contextlib.py", line 153, in __exit__
self.gen.throw(typ, value, traceback)
File "C:\Program Files\Python310\lib\site-packages\pip\_vendor\urllib3
esponse.py", line 443, in _error_catcher
raise ReadTimeoutError(self._pool, None, "Read timed out.")
pip._vendor.urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='files.pythonhosted.org', port=443): Read timed out.
WARNING: You are using pip version 21.2.3; however, version 22.3.1 is available.
You should consider upgrading via the 'C:\Program Files\Python310\python.exe -m pip install --upgrade pip' command.
I have this problem can you help me fixit sir
ValueError: Object arrays cannot be loaded when allow_pickle=False
Your dataset is not proper , make your dataset again
Is it good for final yr project
It's a small project and not suitable if you are making it in a group of 3-4 members
Attribute error:- no shape
Ye aa raha mera
hello ...sir i need ur help
Is this a cnn model ?
It's a lstm model
Brother mp data is create for only A,B,C 🥺
It doesn't store other alphabetic 🥺🥺
You have to update action list in function .py file
BHAI VIDEO MAIN A KE 29.NPY FILE DIKHAYE MAGAR DIYE SIRF 14
BAAKI KE BHI DEDO PLEASE SCHOOL KA PROJECT HAIN AAPKA NAAM LIKH DUNGA INSPIRATION MAIN
jo video ke time pe 3 alphabets ke dataset bnae hai vo h 30 but jo alag dataset bnaya tha sabhi alphabet ke liye usme mere pass sirf 15 ka hi set h
Can we use your code and dataset?
Yes, code links are in description box
@@ProgresswithPython not able to install mediapipe
Could not find a version that satisfies the requirements mediapipe
Your 1st link for A B C data images only shows images. Second link of all alphabets does not show images
Second link contains datasets of all images
@@ProgresswithPython In your first link if we click of A folder directly images are shown.
But on second link if we click on A folder there are other folders 0,1,2.... On clicking them it shows .npy and and on clicking npy file images are not shown