prerakmody

"""
Motivation: Understanding Convolution for Semantic Segmentation (https://arxiv.org/pdf/1702.08502.pdf) 
          : https://stats.stackexchange.com/questions/265462/whats-the-receptive-field-of-a-stack-of-dilated-convolutions
"""

import pdb
import traceback
import numpy as np
import matplotlib.pyplot as plt

prerakmody

import gc
import sys
import humanize # pip install humanize

def actualsize(input_obj):
    # https://towardsdatascience.com/the-strange-size-of-python-objects-in-memory-ce87bdfbb97f
    memory_size = 0
    ids = set()
    objects = [input_obj]
    while objects:

prerakmody

Useful aliases

Add these aliases in your ~/.bashrc file. To use them, save the updated file and type . ~/.bashrc to reload the bash file

1. View all running jobs

   • alias qq="watch -n 0.1 'squeue -u ppmody -o \"%.10i %.9P %.24j %.8u %.2t %.10M %.5D %R\" ; echo -e \"\n\" ; squeue -p LKEBgpu,highmemgpu,gpu --sort=\"N,-i\" -o \"%.10i %.9P %.12j %.8u %.2t %.10M %.5D %.16R %.3C %.7m %b\"; echo -e \"\n\"; sinfo -a' "
     

2. View resources within the cluster

   • alias qqq="scontrol -o show nodes |grep -e \"lkeb\" -e \"gpu.ai\" -e \"gpu\"| awk '{ print \$1, \$4, \$5, \$9, \$23, \$24, \$25}'"
     

prerakmody

"""
This script shall plot contours using cv2 on an image
- Useful for plotting organ contours on a medical image
-- Note: Organ Mask should contain labels values in the [0,255] range 
"""

# Standard Libraries
import pdb
import cv2
import numpy as np

prerakmody

"""
References

1. Calculating area under the curve (AUC) using Riemann Sum - https://en.wikipedia.org/wiki/Riemann_sum
2. https://scikit-learn.org/stable/modules/generated/sklearn.metrics.auc.html#sklearn.metrics.auc
 - it uses np.trapz()
    - Code: https://github.com/numpy/numpy/blob/v1.22.0/numpy/lib/function_base.py#L4686-L4797
3. Other methods implemented in TFlow
    - https://wikidocs.net/24605
    - Note: This method only works right when we provide a list x that has evenly spaced values

prerakmody

"""
OG Ref: https://github.com/tensorflow/probability/issues/620

Goals
 - To experiment with DNNs built using Flipout layers in both eager and non-eager mode
    - Eager mode allows for debugging using tf.print()
    - Non-eager mode is supposed to be faster and less memory consuming since its pre-computes functions in a graph 
 - Models will be made using functional API and the dataset will not use tf.data.Dataset

Notes

prerakmody

"""
Understanding Entropy and Mutual information (epistemic uncertainty) with Stochastic Forward Passes (=M)
Binary Classification
 - y = {(p1, (1-p1)), (pn, (1-pn)), ... (pn, (1-pn))}
 - Ent  = -(pbar.log(pbar) + (1-pbar).log(1-pbar))
 - MIF  = Ent + avg_M(p1.log(p1) + ... + pn.log(pn) + (1-p1).log(p1) + ... + pn.log(1-pn))

 - Case1 
 -- y = {(1,0), (1,0), ..., (1,0)}
 -- pbar = (1,0)

prerakmody

import numpy as np
import matplotlib
import matplotlib.pyplot as plt

cmap = matplotlib.cm.get_cmap('magma')
f,axarr = plt.subplots(1,3)

x   = np.arange(0,1,0.01)
img = np.zeros((len(x),len(x),4))
for x_id, x_ in enumerate(x):img[x_id,:,:] = np.repeat(np.expand_dims(np.array(cmap(x_)), axis=0), len(x), axis=0)

prerakmody

import skimage
import skimage.measure
import plotly.graph_objects as go

voxel_mask = #
verts, faces, _, _ = skimage.measure.marching_cubes(voxel_mask, step_size=1)

fig = go.Figure(data=[go.Mesh3d(x=verts[:,0], y=verts[:,1], z=verts[:,2], i=faces[:,0],j=faces[:,1],k=faces[:,2])])
fig.write_html('tmp.html') # in VS-Code install the "HTML Preview" extension (Analytic Signal Limited)
fig.show()

prerakmody

"""
pip install tensorflow
pip install tf2onnx keras2onnx onnxmltools
"""

import os
import pdb
import json
import traceback
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"