akshaybahadur21 / emojinator Goto Github PK

View Code? Open in Web Editor NEW

499.0 32.0 191.0 321.71 MB

A simple emoji classifier for humans. 🖖

License: MIT License

Python 86.52% Starlark 13.48%

emojinator gesture frame python deep-learning object-detection opencv computer-vision

emojinator's Introduction

Emojinator 🖖

This code helps you to recognize and classify different hand emojis

Versions 🗽

Moved to a different Repo 🏺

Description 🤘

Emojis are ideograms and smileys used in electronic messages and web pages. Emoji exist in various genres, including facial expressions, common objects, places and types of weather, and animals. They are much like emoticons, but emoji are actual pictures instead of typographics.

File Organization 🗄️

├── Emojinator Parent (Current Directory)
    ├── Emojinator 
        ├── CreateGest.py : Create Gestures 
        ├── TrainEmojinator.py : Train Machine Learning model
        ├── Emojinator.py : Emojinator Application
        ├── gestures : Gesture folder
            ├── 0/
            ├── 1/
            .
            .
            .
            └──11/
        └── hand_emo : hand emojis used in prediction
            ├── 0.png
            .
            .
            └── 12.png
    ├── Emojinator_V2 
    ├── LICENSE
    └── readme.md

Results 📊

Emojinator

Emojinator 2.0

Emojinator 3.0

Rock Paper Scissor Lizard Spock

EmoGram

📌 Cite Us

To cite this guide, use the below format:

@article{emojinator,
author = {Bahadur, Akshay},
journal = {https://github.com/akshaybahadur21/Emojinator},
month = {01},
title = {{Emojinator}},
year = {2018}
}

Made with ❤️ and 🦙 by Akshay Bahadur

emojinator's People

Contributors

Stargazers

Watchers

Forkers

adolfoeliazat godfatherace ayushagarwal286 sumedhsonkamble binhudakhalid aswanipranjal katamit madhumitha16 paojianghu shikharateverest pythnist hidhineshraja manishmittal9 nilopc-python diveshuttam mazilong vikasmech dionwang88 deepartificial turpure paras16jul1991 vivekprcs hari5004 gautamamber belphy16 ahmedfadhil ssh-shashi harshit-mehtaa nikhilabhiman jameslin2014 snmjack noorulhasan06 mayank-17 kalyanking11 kvsdurgasuresh hunter125555 vishaljindal09 owlyone vodkada alianglan dyg123 liuxiaoqiang wangtuo0820 yaduvendra srajagop jplayer-top likaitop ud20496 pujoseno rachidbel vikassangwan003 developer-alpha abhi-jha printedheart arvind-india wajih-sid ankitnamdeo34 adi1729 mjsoltysiak jesbr7 rayjvillicana khenghorngganedwin trinhquocnguyen nikhii shoryasiddharth lucky-119 nkrth shambhavik142 akhilbhat060890 parampopat shashgpt ersawant mohan67nv ramonfontes djairmaykon saushe adfmb aks060 piyushchoudhary17 akankshap12 aravind1444 anurag-patwegar manojbalaji1 joshuagithub ashwinb-hat p4thakur diwanshib samrudh chaitanybhardwaj97 shubhampachori12110095 jaykimbravekjh rajpratim vidyasagarpogiri selvajk hieuqtran svoit joeledwards372 rarenicks mshtyusuf anandprabhakar0507

emojinator's Issues

Index Error during keras predict class

Hello sir,
I'm trying this code. I had used 10 gestures and in hand_emo folder uploaded 11 photos. Whenever m trying to execute main program of emojinator final program in which we are overlaying images I'm getting error in line
img=overlay(img,emojis[predict_class],400,300,350,350)
The error is: list index out of range
I trid printing values of predict_class which is 15 and emojis is from 0-10. Is this error due to mismatch in these values. Also kindly explain me how predict class is calculated.

Error in creategesture

I get some error,after typing the number of the gesture

error: OpenCV(4.0.0) D:\Build\OpenCV\opencv-4.0.0\modules\imgproc\src\shapedescr.cpp:272: error: (-215:Assertion failed) npoints >= 0 && (depth == CV_32F || depth == CV_32S) in function 'cv::contourArea'

don't know how to solved it @@

Is it possible to create another folder containing just the images.

I am trying to clone and it is taking forever.

I just want to download and it is taking forever - there is a folder with lots of images and that's holding up the cloning .

I liked your project and following it. Trying to see how you are doing it using the CNN.

showing error in making gestures

cv2.error: OpenCV(4.1.1) C:\projects\opencv-python\opencv\modules\imgproc\src\shapedescr.cpp:274:

error in createget.py

error Traceback (most recent call last)
in ()
76
77 g_id = input("Enter gesture number: ")
---> 78 main(g_id)

in main(g_id)
27 ret, frame = cap.read()
28 frame = cv2.flip(frame, 1)
---> 29 hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
30
31 mask2 = cv2.inRange(hsv, np.array([2, 50, 60]), np.array([25, 150, 255]))

error: OpenCV(3.4.2) /io/opencv/modules/imgproc/src/color.hpp:253: error: (-215:Assertion failed) VScn::contains(scn) && VDcn::contains(dcn) && VDepth::contains(depth) in function 'CvtHelper'

ERROR: Emojinator v2 is not running

Emojinator v2 is apparently not writing. Have imported the cv2 module but the problem perseus.

Excellent job!

Excellent job ! 👍
Could you please tell me why you design network like this?
What's your purpose when you add each layer?

model.add(Conv2D(32, (5, 5), input_shape=(image_x, image_y, 1), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')) model.add(Conv2D(64, (5, 5), activation='sigmoid')) model.add(MaxPooling2D(pool_size=(5, 5), strides=(5, 5), padding='same')) model.add(Flatten()) model.add(Dense(1024, activation='relu')) model.add(Dropout(0.6)) model.add(Dense(num_of_classes, activation='softmax'))

Please Help

I am using Terminal for all python programming.
successfully executed first 2 files but ran into an error when tried running "TrainEmojinator.py".
This is the error I encountered.
Please Help.

Using TensorFlow backend.
number of training examples = 1199
number of test examples = 0
X_train shape: (1199, 2500)
Y_train shape: (1, 1199)
X_test shape: (0, 2500)
Y_test shape: (1, 0)
Traceback (most recent call last):
File "TrainEmojinator.py", line 82, in
main()
File "TrainEmojinator.py", line 63, in main
train_y = np_utils.to_categorical(Y_train)
File "/Users/Saransh/anaconda2/lib/python2.7/site-packages/keras/utils/np_utils.py", line 23, in to_categorical
y = np.array(y, dtype='int')
ValueError: invalid literal for long() with base 10: 'es/1'

Issue in code

The same code gives a few errors.
The first one is that mkdir command doesn't work as intended.
The second one is the contour function of cv2. It doesn't launch the camera also.

Not able to create new images. I am using code present in CreateGest to create new images. The code is running and the camera is switching ON as well but when i show my hand to create new images the new images are not being added to the folder. The counter present on the left bottom of the screen when camera is opened is also not increasing

Rename readme file to README.md

Training an new model

What changes I need to make in the TrainEmojinator.py file for training a new model with a different number of classes and a different number of training images?

LICENCE missing

Is this code available under terms of some open source licence?? I want to use it for some of my own projects so if you can add a LICENCE it would be great.

Issue: Saving Image

Sir,
Everything is fine but the images are not saving in the given path. And, also can we convert the code into an application? Kindly help me to resolve this issue.
Sohana Tarafder

Error in Emojinator_V2.py (detector_utils.py), Session error

Traceback (most recent call last):
File "Emojinator_V2.py", line 10, in
detection_graph, sess = detector_utils.load_inference_graph()
File "D:\1Downloads\Emojinator-master (1)\Emojinator-master\Emojinator_V2\utils\detector_utils.py", line 45, in load_inference_graph
sess = tf.Session(graph=detection_graph)
AttributeError: module 'tensorflow' has no attribute 'Session'

Issue with running emojinator.py

i am getting following index error while running emojinator.py:

IndexError Traceback (most recent call last)
in
----> 1 main()

in main()
28 pred_probab, pred_class = keras_predict(model, newImage)
29 print(pred_class, pred_probab)
---> 30 img = overlay(img, emojis[pred_class], 400, 250, 90, 90)
31
32 x, y, w, h = 300, 50, 350, 350

IndexError: list index out of range

what i am doing wrong? any solution?

Program not working

Hi, I was following the procedure, I ran the CreateGest.py and entered the gesture name but no frames are getting displayed.

Error in Emojinator_V2.py (detector_utils.py), GraphDef error

Traceback (most recent call last):
File "Emojinator_V2.py", line 10, in
detection_graph, sess = detector_utils.load_inference_graph()
File "D:\1Downloads\Emojinator-master (1)\Emojinator-master\Emojinator_V2\utils\detector_utils.py", line 40, in load_inference_graph
od_graph_def = tf.GraphDef()
AttributeError: module 'tensorflow' has no attribute 'GraphDef'

Error in Emojinator_V2.py (label_map_util.py)

(myenv1) D:\1Downloads\Emojinator-master (1)\Emojinator-master\Emojinator_V2>python Emojinator_V2.py
2021-11-24 15:52:31.974645: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
Traceback (most recent call last):
File "Emojinator_V2.py", line 1, in
from utils import detector_utils as detector_utils
File "D:\1Downloads\Emojinator-master (1)\Emojinator-master\Emojinator_V2\utils\detector_utils.py", line 28, in
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
File "D:\1Downloads\Emojinator-master (1)\Emojinator-master\Emojinator_V2\utils\label_map_util.py", line 116, in load_labelmap
with tf.gfile.GFile(path, 'r') as fid:
AttributeError: module 'tensorflow' has no attribute 'gfile'

got error in get_hand_images.py

$ python3.6 get_hand_images.py

VIDEOIO ERROR: V4L2: Pixel format of incoming image is unsupported by OpenCV
Unable to stop the stream: Device or resource busy
VIDEOIO ERROR: V4L: can't open camera by index 0
Traceback (most recent call last):
File "get_hand_images.py", line 28, in
main()
File "get_hand_images.py", line 22, in main
cv2.imshow("Capturing gesture", frame)
cv2.error: OpenCV(3.4.3) /io/opencv/modules/highgui/src/window.cpp:356: error: (-215:Assertion failed) size.width>0 && size.height>0 in function 'imshow'

Maybe I missed something or version related problem. Could you please help me?
Thanks in advance.

Error in Creategest.py

When I'm running the code this comes.
cv2.error: OpenCV(4.2.0) C:\projects\opencv-python\opencv\modules\imgproc\src\shapedescr.cpp:315: error: (-215:Assertion failed) npoints >= 0 && (depth == CV_32F || depth == CV_32S) in function 'cv::contourArea'

please help to rectify it.

CreateGest.py and get_hand_images.py both are not working

Hi, CreateGest.py and get_hand_images.py both are not working for me. even after videocapture(0) it is not able to start camera. I tried playing with while loop then it started camera, but as i am new to python and ML both i was not able to successfully execute it.

./CreateGest.py:

By default, 'file' is written in the MIFF image format. To
specify a particular image format, precede the filename with an image
format name and a colon (i.e. ps:image) or specify the image type as
the filename suffix (i.e. image.ps). Specify 'file' as '-' for
standard input or output.
import: delegate library support not built-in '' (X11) @ error/import.c/ImportImageCommand/1297.
./CreateGest.py: line 5: image_x,: command not found
./CreateGest.py: line 7: syntax error near unexpected token (' ./CreateGest.py: line 7: cap = cv2.VideoCapture(0):'

how use hand_detection_inference_graph for training

Hello @akshaybahadur21 ,

so amazing.
I am a little bit interested that how to make use of your uploaded model in hand_detection_inference_graph.
Could you show me the detailed steps? thanks a lot.

Best Regards,
kingaza

ValueError: invalid literal for int() with base 10: 'es\\3'

I tried to reduce classes to 6. Changed num_of_classes in TrainEmojinator.py. Also removed gestures from 7 to 12
However getting below error while training the model:
y = np.array(y, dtype='int')
ValueError: invalid literal for int() with base 10: 'es\3'

In main function:
main()
File ".\TrainEmojinator.py", line 61, in main
train_y = np_utils.to_categorical(Y_train)

Got error in CreateGest.py

When i am executing CreateGest.py I was getting this error

File "CreateGest.py", line 42, in main
if len(contours) > 0:
TypeError: object of type 'NoneType' has no len()
[ WARN:0] terminating async callback
[ WARN:0] terminating async callback

Please help me in solving this. Thanks in advance.