search

lindawangg / COVID-Net

COVID-Net Open Source Initiative
Other
1.15k stars 480 forks source link

Can you provide pretrained model on imageNet? #27

Closed Kyfafyd closed 4 years ago

Kyfafyd commented 4 years ago

Issue Template

Description

Please include a summary of the issue. Please include the steps to reproduce. List any additional libraries that are affected.

Steps to Reproduce

  1. First step
  2. Second step
  3. Third step

Expected behavior

A description of what you expected to happen.

Actual behavior

A description of what happens instead.

Environment

zeeshannisar commented 4 years ago

Dear @Kyfafyd if you are asking for Pre-trained models used for detecting and visualizing the COVID-19 you can refer to my GitHub Reposiotory where I used three different Pre-trained Networks (VGG16, VGG19, and DenseNet121) for COVID-19 identification for the same data provided by the authors of COVID-Net. I hope it would help you for what you are asking for.

AasiaRehman commented 4 years ago

What is this error about?? img = cv2.resize(img, INPUT_SIZE) # resize cv2.error: OpenCV(3.4.2) C:\Miniconda3\conda-bld\opencv-suite_1534379934306\work\modules\imgproc\src\resize.cpp:4044: error: (-215:Assertion failed) !ssize.empty() in function 'cv::r

zeeshannisar commented 4 years ago

@AasiaRehman can you please share the complete code for which you are having an error? As per my understanding, your img array is empty and hence it's giving an error while resizing. For me, the best is to read and resize the image with the following line of code.

import tensorflow as tf
img = tf.keras.preprocessing.image.load_img(img_path, target_size=(width, height), color_mode='grayscale/rgb', interpolation='nearest')
Kyfafyd commented 4 years ago

@lindawangg Can you please provide the pretrained model on ImageNet? Thanks a lod!