Don't we need to divide L channel by 100 since original values vary between 0 to 100? https://github.com/bnsreenu/python_for_microscopists/blob/master/090a-autoencoder_colorize_V0.2.py#L47

Same needs to be applied during prediction here https://github.com/bnsreenu/python_for_microscopists/blob/master/090a-autoencoder_colorize_V0.2.py#L112.

Anyway nice tutorial. Thanks.

Hey there!

For: 264_alibinet_outlier_detection.py

Where it says: from alibi_detect.utils import save_detector, load_detector

It should say: from alibi_detect.utils.saving import save_detector, load_detector

Hello Sreeni,

Thanks for your excellent learning courses, they are really amazing! Could you please explain a little about the attached images which are taken from your GitHub page? Is there any document that I can read about these images?

Thanks for your favor

Hello Sreeni,

Thank you for the awesome tutorial videos. I followed the youtube tutorial to make a container on my ubuntu-os system and faced a few issues did not happen in tutorial. Though I exerted the suggestions in web the problem was not solved and would appreciate it if you can guide me here. in the beginning the terminal generated this error: _no such option: --no-cashe-dir The command '/bin/sh -c pip install --no-cashe-dir -r requirements.txt' returned a non-zero code: 2_ when running the last command in Dockerfile: RUN pip install --no-cashe-dir -r requirements.txt

and when running sudo docker run -v for mapping, I faced a long-standing issue: _docker: invalid reference format_

I could not solve this problem looking to web and thought maybe you might figure what went wrong.

Respectfully Nilla

Hi, First thanks a lot for your very useful and productive videos and codes. May I ask you please teach me how to predict the COVID with SEIR model and fit the data with SEIR model ... I saw your codes and video with exponential growth, not SEIR

Thanks

Hi @bnsreenu

Firstly, thank you very much for the amazing videos. I am sorry, this is not really an issue.

I've a few doubts in reading czi file and I would like to ask those here. Following the video tutorial, the czi file is imported in python like this

import czifile
from skimage import io

img = czifile.imread('file.czi')
print(img.shape)

The output is (1, 1, 3, 1, 48, 1024, 1024, 1) I couldn't completely understand what each value in the output refers to

Does 3 denote the number of channels? Does 48 denote the number of slices in the z-stack for each channel?

I would like to save the z-stack corresponding to channel 1 in tiff format. Could you please offer some advice on how this can be done?

Hi, I have applied this model to other data sets. I want to forecast the energy consumption using a history of energy consumption and 23 weather features over 4 years.

The validation loss is increasing, which I assume it is a sign of overfitting. and the training loss does not go under 0.2. I have tried decreasing the learning rate, adding decay rate, and reducing the lstm layers, but I still have overfitting.

How can I modify my model to prevent overfitting (the increasing trend in the validation loss?

Thanks for any advice.

hi i have a problem with import function image loader in third part how to import a function from another file? and also in validation folder we dont have mask so if we want to use validation folder for validate our model how should i do?

@bnsreenu Thank you for great tutorials ! I'm having trouble pre-processing for 3D object tracking with trackpy, I have multi-channel, multi-tile z-stack images in "czi" format directly out from Zeiss and having trouble setting up these files for tutorial compatible format. any guidance would highly be appreciated!

hi every one I have a question about this phase of image preprocessing. Does this huge dataset need use filter for remove noise?? which filter is the best?(new one)and Do we have a python source for preprocessing step of BRATS2020 for learning more? Which course or library is the best for dataset BRATS2020?