prajnasb / observations Goto Github PK

Would you be willing to add a license to this repository?

Why i am getting this error?

Hello,
Thank you for sharing your code. I try to execute it but this error is appeared FileNotFoundError: [Errno 2] No such file or directory: 'mask1_model_resnet50.pth'
Can you please share this file?
Thank you

In line 137 of Data_Generator/mask.py, PIL's rotate function expects the rotation angle to be in degrees, but as np.arctan2 returns in units of radians, there is almost no rotation applied any time. This makes the code not work properly for tilted faces. Please look into it.

I follow your blog on COVID-19 face mask detection.
I wanted to reproduce my own dataset. so i referred to this repository. I cloned a copy to use it.
In .\observations-master\mask_classifier\Data_Generator\mask.py line 67 you've imported face_recognition. But then you never mentioned from where you imported. It would be easy if you share even that part or even mention what is alternative way.
Thank you.

there is an issue with git clone "url" it says checkput failed and cloning cancelled

It would be helpful if someone could add the execution details on how to run the code.

The dataset is amazing. The only issue is color of masks. in all the images the color of mask is same. when a mask of different color is bought to test the model gives up! add some images with colorful masks

The dataset which you have created, have you uploaded it on Kaggle or any other online platform to use it directly?

While executing webcam.py , I encoutered following error:

_**_ModuleNotFoundError Traceback (most recent call last)

in ()
5 from pygame import mixer
6 import time
----> 7 from label_detect import classify_face
8
9

ModuleNotFoundError: No module named 'label_detect'**

I am using google colab with GPU.
Thanks in advance!

Since the images are of different sizes, we can add a piece of code to resize the images so that they become of same sizes.

I have already done that locally.

Currently not enough information about how to install the required packages is presented, for example it is needed python 3.7 in order to install pygame 1.9.6. Moreover, the mkl packages versions specified on the requirements file are only available on anaconda cloud, not on pypi.

Hi
Which part in your code is for data augmentation ?

Helllo
These are the missing modules for this project:
torch
totchvision
pygame
matplotlib
pandas
sklearn

Hi, I am facing error when run the model_fit cell. However, I found the photo is inside the folder.
OSError: cannot identify image file <_io.BufferedReader name='observations/experiements/dest_folder/train\without_mask\indian-ethnicity-cheerful-confident-studio-260nw-552325924.jpg'>
Thanks.

WZ

First of all, thank you for making this wonderful program.

I'd like to create data on people who don't wear masks to their noses in your program.

what should i do and Where should I fix your code?

I'd appreciate it if you'd reply. Have a greate day!

label = classify_face(image)

File "label_detect.py", line 62, in classify_face
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
cv2.error: OpenCV(4.4.0) C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-2b5g8ysb\opencv\modules\imgproc\src\color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'

Since praj.jpg is not given I tried using my image but still the error remains..Is there any requirement for the image used

The model I saved after runnning training.ipynb is resnet101 but the model used is resnet50 ..Is this a mistake in the naming of models or are these two different models?