prerakmody

raw_output = net.layers['conv6']
 
# Step1 : 
raw_prediction = tf.reshape(raw_output, [-1, args.num_classes])
label_proc = prepare_label(label_batch, tf.stack(raw_output.get_shape()[1:3]), num_classes=args.num_classes, one_hot=False) # [batch_size, h, w]
raw_gt = tf.reshape(label_proc, [-1,])
indices = tf.squeeze(tf.where(tf.less_equal(raw_gt, args.num_classes - 1)), 1)
 
# Ste2 : 
gt = tf.cast(tf.gather(raw_gt, indices), tf.int32)    

prerakmody

def mrcnn_mask_loss_graph(target_masks, target_class_ids, pred_masks):
    """Mask binary cross-entropy loss for the masks head.
    target_masks: [batch, num_rois, height, width].
        A float32 tensor of values 0 or 1. Uses zero padding to fill array.
    target_class_ids: [batch, num_rois]. Integer class IDs. Zero padded.
    pred_masks: [batch, proposals, height, width, num_classes] float32 tensor
                with values from 0 to 1.
    """
    # Step1.1 : Reshape for simplicity. Merge first two dimensions into one.
    target_class_ids = K.reshape(target_class_ids, (-1,))

prerakmody

# from scapy3k.all import *
import sys
print (' - Encoding : ', sys.getdefaultencoding())
# print (' - Version  : ', sys.version)

import math
import pprint
import datetime
import pandas as pd
from scapy.all import * #https://scapy.readthedocs.io/en/latest/installation.html

prerakmody

import h5py
import numpy as np

filename = 'filename.h5'
data     = h5py.File(filename)
nodes    = list(data.items())
data_path= '/a/b' #mention the node you are interested in

#Convert to .csv
filename_save = 'filename.csv'

prerakmody

import os
import re
import sys
import copy
import struct
import pprint
import traceback

def pcd_read(filename, verbose=0, verbose_steps=0):
    # Refer this to unpack - https://docs.python.org/3/library/struct.html#format-characters

prerakmody

import time
import tqdm
import colorama # for multiple tqdm bars on Windows
import numpy as np

dataloader = np.random.random((10))

with tqdm.tqdm(total=len(dataloader), leave=True, disable=False, position=0) as pbar:
  for val in dataloader:
    pbar.update(1)

prerakmody

AWS command line utility for S3

Install

• sudo pip3 install awscli

Configure

• cd ~/
• mkdir ~/.aws
• vim ~/.aws/config

[default]

prerakmody

Generate certificate

1. Visit certbot
2. Follow the steps for your particular OS

prerakmody

Installation

0. Spin up an AWS/Azure/GCP machine (Ubuntu - 16.04)
   • ensure you know how to use the web-interface of these IaaS to open ports for an instance
   • open ports 80, 443, 8000, 8888
1. Follow this link
2. Create a dir (.jupyterhub) which shall contain jupyterhub specific files
   • mkdir .jupyterhub
   • cd .jupyterhub
   • jupyterhub --generate-config
   • openssl rand -hex 8 > jupyterhub_cookie_secret

prerakmody

Installation

1. Windows (ros-noetic with pytorch)

   conda create -y -n XOSight-Pattern2 "python=3.8" "mamba>=0.22.1" -c conda-forge
   conda activate XOSight-Pattern2
   mamba install ros-noetic-desktop -c robostack -c robostack-experimental -c conda-forge --override-channels
   mamba install vs2019_win-64
   conda deactivate
   conda activate XOSight-Pattern2
   

mamba install rosdep