hav4ik

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

sns.set()

def ndcg_at_k(ranked_relevances, k=None):
    """
    Calculate NDCG for given ranked relevances.
    """

hav4ik

import cv2
import copy
import pycocotools.mask as mask_util
import numpy as np


class CopyPasteAugmentator:
  """Copy-paste cells from another image in the dataset
  """
  def __init__(self, d2_dataset,

hav4ik

class YourAgent:
  def __init__(self,
               # ... other params
               # ...
               antigeo_thresh=20):
    
    # ...
    # Initialize your agent here ...
    # ...
    

hav4ik

import operator
import numpy as np
import cmath
from collections import namedtuple


basis = np.array([1, cmath.exp(2j * cmath.pi * 1 / 3), cmath.exp(2j * cmath.pi * 2 / 3)])
HistMatchResult = namedtuple("HistMatchResult", "idx length")

hav4ik

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1096                 batch_size=batch_size):

hav4ik

# These are probably the only important parameters in the
# whole pipeline (steps 0 through 3).
BLOCK_SIZE = 40
DELTA = 25

# Do the necessary noise cleaning and other stuffs.
# I just do a simple blurring here but you can optionally
# add more stuffs.
def preprocess(image):
    image = cv2.medianBlur(image, 3)

hav4ik

# Somehow I found the value of `gamma=1.2` to be the best in my case
def adjust_gamma(image, gamma=1.2):
    # build a lookup table mapping the pixel values [0, 255] to
    # their adjusted gamma values
    invGamma = 1.0 / gamma
    table = np.array([((i / 255.0) ** invGamma) * 255
        for i in np.arange(0, 256)]).astype("uint8")

    # apply gamma correction using the lookup table
    return cv2.LUT(image, table)

hav4ik

mnetv2:    601833648 FLOPs
alexnet:  2079939473 FLOPs
vgg19:   39285112688 FLOPs
vgg16:   30960211824 FLOPs


body_0:    208719616 FLOPs
mood_head: 396661522 FLOPs
roa_head:   68190732 FLOPs
art_head:  396730804 FLOPs

hav4ik

Install Nvidia drivers the right way

You don't want Xorg to use your NVIDIA gpu. Need to blacklist nouveau and nvidia-drm. In the created file /etc/modprobe.d/blacklist-nouveau.conf:

blacklist nouveau
options nouveau modeset=0

In the file /etc/modprobe.d/blacklist-nvidia-drm.conf:

blacklist nvidia-drm

hav4ik

" ------------------- BEGIN: VUNDLE CONFIGURATION -------------------
set nocompatible   " required
filetype off       " required

" set runtime path to include Vundle and initialize
set rtp+=~/.vim/bundle/Vundle.vim
call vundle#begin()

" let Vundle handle itself, required!
Plugin 'VundleVim/Vundle.vim'