Martin Weigert maweigert

## coin_flip.py
"""
Flip a fair coin 100 times—it gives a sequence of heads (H) and tails (T).
For each HH in the sequence of flips, Alice gets a point; for each HT, Bob does,
so e.g. for the sequence THHHT Alice gets 2 points and Bob gets 1 point.
Who is most likely to win?


https://x.com/littmath/status/1769044719034647001?s=20


## arxiv latex
# Makefile to create arxiv submission conforming single latex files. Created originaly by Uwe Schmidt

all: pdf


pdf: main.tex
	pdflatex main.tex
	# http://stackoverflow.com/a/21935690
	-biber main
	pdflatex main.tex

## environment.yaml
name: dl-image-mw
channels:
  - defaults
  - nvidia
dependencies:
  - python=3.9
  - cudatoolkit=11.0.*
  - cudnn=8.0.*
  - jupyter
  - numpy

## set_batchnorm_momentum.py
"""
The default momentum of MobileNet (for running average calculation) in tf seems to be very high (0.99?), resulting in huge (and suprising) differences in train vs evaluate loss

https://github.com/keras-team/keras/issues/6977

Setting it to something sensible (e.g. 0.9) fixes this

https://stackoverflow.com/questions/65415799/fit-works-as-expected-but-then-during-evaluate-model-performs-at-chance/66692755#66692755
"""

## downsample_gpu.py
# Average-Downsampling example in OpenCL (via gputools)
# please install it first via
# pip install gputools

import numpy as np
from gputools import OCLProgram, OCLArray, get_device
from timeit import default_timer
from skimage.transform import downscale_local_mean

# opencl kernel

## stardist_memory.py
import tensorflow as tf
import numpy as np
import psutil
import os
from stardist.models import Config3D, StarDist3D

os.environ['CUDA_VISIBLE_DEVICES']= "0"# '1,0'

from tensorflow.keras.utils import Sequence
import stardist

## qupath_export_annotations.groovy
/* QuPath-Script to export annotations to label tif images (e.g. to be used for stardist)

 Use "Run for project" to export annotations for all images within a QuPath project

 Afterwards both images and mask tiffs will be stored in the project subfolder

 ground_truth
 ├── images
 └── masks


## matching_metrics.py
import numpy as np
import matplotlib.pyplot as plt
from scipy.ndimage import label, zoom

from stardist.matching import matching
from stardist.plot import render_label, render_label_pred
np.random.seed(42)

def create_example():
    rand_gt = np.random.uniform(0,1,(8,8))

## label_image_from_rois.py
#@ ImagePlus imp
#@ OUTPUT ImagePlus result

from ij import IJ
from ij.plugin.frame import RoiManager

result = IJ.createImage("Labeling", "16-bit black", imp.getWidth(), imp.getHeight(), 1)
ip = result.getProcessor()
rm = RoiManager.getInstance()

## stardist_noto_setup.sh
#!/usr/bin/env bash

source ~/.bashrc

git clone https://github.com/mpicbg-csbd/stardist

my_venvs_create stardist_env
my_venvs_activate stardist_env
pip install tifffile==2019.7.2   # as newer versions somehow wont install on noto
pip install stardist
	"""
	Flip a fair coin 100 times—it gives a sequence of heads (H) and tails (T).
	For each HH in the sequence of flips, Alice gets a point; for each HT, Bob does,
	so e.g. for the sequence THHHT Alice gets 2 points and Bob gets 1 point.
	Who is most likely to win?


	https://x.com/littmath/status/1769044719034647001?s=20
	# Makefile to create arxiv submission conforming single latex files. Created originaly by Uwe Schmidt

	all: pdf


	pdf: main.tex
	pdflatex main.tex
	# http://stackoverflow.com/a/21935690
	-biber main
	pdflatex main.tex
	name: dl-image-mw
	channels:
	- defaults
	- nvidia
	dependencies:
	- python=3.9
	- cudatoolkit=11.0.*
	- cudnn=8.0.*
	- jupyter
	- numpy
	"""
	The default momentum of MobileNet (for running average calculation) in tf seems to be very high (0.99?), resulting in huge (and suprising) differences in train vs evaluate loss

	https://github.com/keras-team/keras/issues/6977

	Setting it to something sensible (e.g. 0.9) fixes this

	https://stackoverflow.com/questions/65415799/fit-works-as-expected-but-then-during-evaluate-model-performs-at-chance/66692755#66692755
	"""
	# Average-Downsampling example in OpenCL (via gputools)
	# please install it first via
	# pip install gputools

	import numpy as np
	from gputools import OCLProgram, OCLArray, get_device
	from timeit import default_timer
	from skimage.transform import downscale_local_mean

	# opencl kernel
	import tensorflow as tf
	import numpy as np
	import psutil
	import os
	from stardist.models import Config3D, StarDist3D

	os.environ['CUDA_VISIBLE_DEVICES']= "0"# '1,0'

	from tensorflow.keras.utils import Sequence
	import stardist
	/* QuPath-Script to export annotations to label tif images (e.g. to be used for stardist)

	Use "Run for project" to export annotations for all images within a QuPath project

	Afterwards both images and mask tiffs will be stored in the project subfolder

	ground_truth
	├── images
	└── masks
	import numpy as np
	import matplotlib.pyplot as plt
	from scipy.ndimage import label, zoom

	from stardist.matching import matching
	from stardist.plot import render_label, render_label_pred
	np.random.seed(42)

	def create_example():
	rand_gt = np.random.uniform(0,1,(8,8))
	#@ ImagePlus imp
	#@ OUTPUT ImagePlus result

	from ij import IJ
	from ij.plugin.frame import RoiManager

	result = IJ.createImage("Labeling", "16-bit black", imp.getWidth(), imp.getHeight(), 1)
	ip = result.getProcessor()
	rm = RoiManager.getInstance()
	#!/usr/bin/env bash

	source ~/.bashrc

	git clone https://github.com/mpicbg-csbd/stardist

	my_venvs_create stardist_env
	my_venvs_activate stardist_env
	pip install tifffile==2019.7.2 # as newer versions somehow wont install on noto
	pip install stardist