WILL LEE BIGBALLON

## extract_ILSVRC.sh
#!/bin/bash
#
# script to extract ImageNet dataset
# ILSVRC2012_img_train.tar (about 138 GB)
# ILSVRC2012_img_val.tar (about 6.3 GB)
# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
#
#  https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
#
#  train/

## radar.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                BIGBALLON
                / radar.ipynb
            
            
              Created
              January 13, 2024 18:52
                — forked from donglixp/radar.ipynb
            
              
                Radar figure in BEiT-3
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## color_log.py
import colorlog
import logging

# 创建日志记录器
logger = colorlog.getLogger(__name__)

# 设置日志级别和格式
logger.setLevel(logging.DEBUG)
formatter = colorlog.ColoredFormatter(
    "%(log_color)s%(levelname)-8s%(reset)s %(log_color)s%(asctime)s | %(blue)s%(message)s",

## imagenet21k_ids_with_classnames.csv
n00004475,organism, being
n00005787,benthos
n00006024,heterotroph
n00006484,cell
n00007846,person, individual, someone, somebody, mortal, soul
n00015388,animal, animate_being, beast, brute, creature, fauna
n00017222,plant, flora, plant_life
n00021265,food, nutrient
n00021939,artifact, artefact
n00120010,hop

## AS.py
"""
# Anomaly Simulation for MVTecAD
# Download describable textures dataset
wget https://www.robots.ox.ac.uk/~vgg/data/dtd/download/dtd-r1.0.1.tar.gz
# Download MVTec anomaly detection dataset
wget https://www.mydrive.ch/shares/38536/3830184030e49fe74747669442f0f282/download/420938113-1629952094/mvtec_anomaly_detection.tar.xz
"""

import os
import random

## EMAE_crop.py
import math
import os
import random
from itertools import product

import numpy as np
from imgaug import augmenters as iaa
from PIL import Image

IMG_SIZE = 600

## resize_with_padding.py
from PIL import Image, ImageOps


def padding(img, expected_size):
    desired_size = expected_size
    delta_width = desired_size - img.size[0]
    delta_height = desired_size - img.size[1]
    pad_width = delta_width // 2
    pad_height = delta_height // 2
    padding = (pad_width, pad_height, delta_width - pad_width, delta_height - pad_height)

## conv.py
import torch

checkpoint = torch.load("resnet18.pth.tar")
state_dict = checkpoint["state_dict"]

from collections import OrderedDict

new_state_dict = OrderedDict()
for k, v in state_dict.items():
    name = k[7:]  # remove 'module.' of dataparallel

## ap_test.py
import numpy as np

def voc_ap(rec, prec):
    # correct AP calculation
    # first append sentinel values at the end
    mrec = np.concatenate(([0.], rec, [1.]))  #[0.  0.0666, 0.1333, 0.4   , 0.4666,  1.]
    mpre = np.concatenate(([0.], prec, [0.])) #[0.  1.,     0.6666, 0.4285, 0.3043,  0.]
    for i in range(mpre.size - 1, 0, -1):
        mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])  #[1.     1.     0.6666 0.4285 0.3043 0.    ]

## .vimrc
" BASIC SETTING
set number
set noswapfile
set autoindent
set cindent
set mouse=a
set encoding=utf-8

set cursorcolumn
set cursorline
	#!/bin/bash
	#
	# script to extract ImageNet dataset
	# ILSVRC2012_img_train.tar (about 138 GB)
	# ILSVRC2012_img_val.tar (about 6.3 GB)
	# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
	#
	# https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
	#
	# train/
	import colorlog
	import logging

	# 创建日志记录器
	logger = colorlog.getLogger(__name__)

	# 设置日志级别和格式
	logger.setLevel(logging.DEBUG)
	formatter = colorlog.ColoredFormatter(
	"%(log_color)s%(levelname)-8s%(reset)s %(log_color)s%(asctime)s \| %(blue)s%(message)s",
	n00004475,organism, being
	n00005787,benthos
	n00006024,heterotroph
	n00006484,cell
	n00007846,person, individual, someone, somebody, mortal, soul
	n00015388,animal, animate_being, beast, brute, creature, fauna
	n00017222,plant, flora, plant_life
	n00021265,food, nutrient
	n00021939,artifact, artefact
	n00120010,hop
	"""
	# Anomaly Simulation for MVTecAD
	# Download describable textures dataset
	wget https://www.robots.ox.ac.uk/~vgg/data/dtd/download/dtd-r1.0.1.tar.gz
	# Download MVTec anomaly detection dataset
	wget https://www.mydrive.ch/shares/38536/3830184030e49fe74747669442f0f282/download/420938113-1629952094/mvtec_anomaly_detection.tar.xz
	"""

	import os
	import random
	import math
	import os
	import random
	from itertools import product

	import numpy as np
	from imgaug import augmenters as iaa
	from PIL import Image

	IMG_SIZE = 600
	from PIL import Image, ImageOps


	def padding(img, expected_size):
	desired_size = expected_size
	delta_width = desired_size - img.size[0]
	delta_height = desired_size - img.size[1]
	pad_width = delta_width // 2
	pad_height = delta_height // 2
	padding = (pad_width, pad_height, delta_width - pad_width, delta_height - pad_height)
	import torch

	checkpoint = torch.load("resnet18.pth.tar")
	state_dict = checkpoint["state_dict"]

	from collections import OrderedDict

	new_state_dict = OrderedDict()
	for k, v in state_dict.items():
	name = k[7:] # remove 'module.' of dataparallel
	import numpy as np

	def voc_ap(rec, prec):
	# correct AP calculation
	# first append sentinel values at the end
	mrec = np.concatenate(([0.], rec, [1.])) #[0. 0.0666, 0.1333, 0.4 , 0.4666, 1.]
	mpre = np.concatenate(([0.], prec, [0.])) #[0. 1., 0.6666, 0.4285, 0.3043, 0.]
	for i in range(mpre.size - 1, 0, -1):
	mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i]) #[1. 1. 0.6666 0.4285 0.3043 0. ]
	" BASIC SETTING
	set number
	set noswapfile
	set autoindent
	set cindent
	set mouse=a
	set encoding=utf-8

	set cursorcolumn
	set cursorline