aditya9211 / blur-and-clear-classification Goto Github PK

command

pip -r install requirements.txt
failed when using python > 3.6+

Dear
I am working on distinguishing blurred images problem. And I think this repertory is interesting and it must be helpful for my work. But I have not yet seen the database used. Could you please tell me which database the repertory had used?

Appreciate your help.

Thanks and regards.

Jasonsey

Hello? I'm working on blur image classification using the network on this site.
I have 2,500 images, and I have blur image and clean image for classification, but when I train,
the validation dataset accuracy is not more than 70% and I have a stagnant problem
Please tell us how can improve our validation accuracy. and I want to know the hyper parameter setting
for your neural network you set.
Thank you

Hi, where are your blur images samples from? Is blur images from some algorithm generated or download a collected image dataset or by google crawler?
Thanks.

Hello, someone else realized a version of this project to run in Colab? I am really interested to try it!!

combined_img = nd.median_filter(combined_img,radius)

Hi - this is great! I've trained my model with 100 blurry and 100 clear and everything seems to be doing well - 96% accuracy, but now for the prediction I can only get it to run one image at a time to give me the good or bad label - am I missing something? I have about 7,000 images to label and I'm looking to set it up for an influx of daily imagery.

The IMAGE_PATH doesn't accept *.jpg or directing it to a folder of images... can you advise?

And then is there an easy way to move the predicted image to a folder based on its label? Trying to get the non-blurry photos to be sent into another NN to be put into a classification model.

Thanks!

Current the orignal size is (320,240) but it needs to be fed from the user though.

want to add predict.py for 1 image to predict blur or clear

and addition to test on the user-defined dataset, not from trained splitter one.

Hi thanks for sharing your work.

but i get this error when running train.py

Train Data Path Success .....
Train Label Path Success .....  
Test Data Path Success .....
Test Label Path Success .....

Saving the splitting results......

Traceback (most recent call last):
 File "train.py", line 564, in <module>
  main()
 File "train.py", line 532, in main
 train_images = np.insert(train_images, 0, 1, axis=1) 
 File "/home/jeniffer/.local/lib/python2.7/site-packages/numpy/lib/function_base.py", line 4431, in   insert
new = empty(newshape, arr.dtype, arrorder)
  MemoryError`

Any ideas?