#!/usr/bin/env python
# coding: utf-8

# <hr style="height:2px;">
# 
# # Demo: Training data generation for combined denoising and upsamling of synthetic 3D data
# 
# This notebook demonstrates training data generation for a combined denoising and upsampling task of synthetic 3D data, where corresponding pairs of isotropic low and high quality stacks can be acquired.
# Anisotropic distortions along the Z axis will be simulated for the low quality stack, such that a CARE model trained on this data can be applied to images with anisotropic resolution along Z.
# 
# We will use only a few synthetically generated stacks for training data generation, whereas in your application you should aim to use stacks from different developmental timepoints to ensure a well trained model. 
# 
# More documentation is available at http://csbdeep.bioimagecomputing.com/doc/.

# In[1]:


from __future__ import print_function, unicode_literals, absolute_import, division
import numpy as np
import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')
get_ipython().run_line_magic('config', "InlineBackend.figure_format = 'retina'")

from tifffile import imread
from csbdeep.utils import download_and_extract_zip_file, plot_some, axes_dict
from csbdeep.io import save_training_data
from csbdeep.data import RawData, create_patches
from csbdeep.data.transform import anisotropic_distortions


# <hr style="height:2px;">
# 
# # Download example data
# 
# First we download some example data, consisting of a synthetic 3D stacks with membrane-like structures.

# In[2]:


download_and_extract_zip_file (
    url       = 'http://csbdeep.bioimagecomputing.com/example_data/synthetic_upsampling.zip',
    targetdir = 'data',
)


# We plot XY and XZ slices of a training stack pair:

# In[3]:


y = imread('data/synthetic_upsampling/training_stacks/high/stack_00.tif')
x = imread('data/synthetic_upsampling/training_stacks/low/stack_00.tif')
print('image size =', x.shape)

plt.figure(figsize=(16,15))
plot_some(np.stack([x[5],y[5]]),
          title_list=[['XY slice (low)','XY slice (high)']],
          pmin=2,pmax=99.8);

plt.figure(figsize=(16,15))
plot_some(np.stack([np.moveaxis(x,1,0)[50],np.moveaxis(y,1,0)[50]]),
          title_list=[['XZ slice (low)','XZ slice (high)']],
          pmin=2,pmax=99.8);


# <hr style="height:2px;">
# 
# # Generate training data for upsampling CARE
# 
# We first need to create a `RawData` object, which defines how to get the pairs of low/high SNR stacks and the semantics of each axis (e.g. which one is considered a color channel, etc.).
# 
# Here we have two folders "low" and "high", where corresponding low and high-SNR stacks are TIFF images with identical filenames.  
# For this case, we can simply use `RawData.from_folder` and set `axes = 'ZYX'` to indicate the semantic order of the image axes.

# In[4]:


raw_data = RawData.from_folder (
    basepath    = 'data/synthetic_upsampling/training_stacks',
    source_dirs = ['low'],
    target_dir  = 'high',
    axes        = 'ZYX',
)


# Furthermore, we must define how to modify the Z axis to mimic a real microscope as closely as possible if data along this axis is acquired with reduced resolution. To that end, we define a `Transform` object that will take our `RawData` as input and return the modified image. Here, we use `anisotropic_distortions` to accomplish this.
# 
# The most important parameter is the subsampling factor along Z, which should for example be chosen as 4 if it is planned to later acquire (low-SNR) images with 4 times reduced axial resolution.

# In[5]:


anisotropic_transform = anisotropic_distortions (
    subsample      = 4,
    psf            = None,
    subsample_axis = 'Z',
    yield_target   = 'target',
)


# From the synthetically undersampled low quality input stack and its corresponding high quality stack, we now generate some 3D patches. As a general rule, use a patch size that is a power of two along XYZT, or at least divisible by 8.  
# Typically, you should use more patches the more trainings stacks you have. By default, patches are sampled from non-background regions (i.e. that are above a relative threshold), see the documentation of `create_patches` for details.
# 
# Note that returned values `(X, Y, XY_axes)` by `create_patches` are not to be confused with the image axes X and Y.  
# By convention, the variable name `X` (or `x`) refers to an input variable for a machine learning model, whereas `Y` (or `y`) indicates an output variable.

# In[6]:


X, Y, XY_axes = create_patches (
    raw_data            = raw_data,
    patch_size          = (32,64,64),
    n_patches_per_image = 512,
    transforms          = [anisotropic_transform],
    save_file           = 'data/my_training_data.npz',
)


# In[7]:


assert X.shape == Y.shape
print("shape of X,Y =", X.shape)
print("axes  of X,Y =", XY_axes)


# ## Show
# 
# This shows a ZY slice of some of the generated patch pairs (odd rows: *source*, even rows: *target*)

# In[8]:


for i in range(2):
    plt.figure(figsize=(16,2))
    sl = slice(8*i, 8*(i+1)), slice(None), slice(None), 0
    plot_some(X[sl],Y[sl],title_list=[np.arange(sl[0].start,sl[0].stop)])
    plt.show()
None;