jainxy

------------------------------
VSCode
https://realpython.com/python-development-visual-studio-code/
https://flaviocopes.com/vscode/
https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.vscode-remote-extensionpack - DONE
------------------------------
RPN notes

https://medium.com/@jonathan_hui/understanding-region-based-fully-convolutional-networks-r-fcn-for-object-detection-828316f07c99 - DONE
https://medium.com/@jonathan_hui/what-do-we-learn-from-region-based-object-detectors-faster-r-cnn-r-fcn-fpn-7e354377a7c9 - DONE

jainxy

About YUV formats

First of all: YUV pixel formats and Recommended 8-Bit YUV Formats for Video Rendering. Chromium's source code contains good documentation about those formats too: chromium/src/media/base/video_types.h and chromium/src/media/base/video_frame.cc (search for RequiresEvenSizeAllocation(), NumPlanes() and those kinds of functions).

YUV?

You can think of an image as a superposition of several planes (or layers in a more natural language). YUV formats have three planes: Y, U, and V.

Y is the luma plane, and can be seen as the image as grayscale. U and V are reffered to as the chroma planes, which are basically the colours. All the YUV formats have these three planes, and differ by the different orderings of them.

jainxy

FFmpeg cheat sheet

A list of useful commands for the ffmpeg command line tool.

Download FFmpeg: https://www.ffmpeg.org/download.html

Full documentation: https://www.ffmpeg.org/ffmpeg.html

Basic conversion

jainxy

"""
A collection of models we'll use to attempt to classify videos.
"""
from keras.layers import Dense, Flatten, Dropout, ZeroPadding3D
from keras.layers.recurrent import LSTM
from keras.models import Sequential, load_model
from keras.optimizers import Adam, RMSprop
from keras.layers.wrappers import TimeDistributed
from keras.layers.convolutional import (Conv2D, MaxPooling3D, Conv3D,
    MaxPooling2D)

jainxy

"""
    Training
    Validation on a holdout set generated from the original training data
    Evaluation on the test data
 - correct and test batch generation
 - Normalize input by 255?
 - add batchnorm layers? use model(x, training=False) then
 - tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(batch_size) ? dataset = dataset.cache()?
 - get_compiled_model()
 - test last batch having non-dividing batch-size aka residual batch issue

jainxy

# Which attributes/features to choose?
# Which model to use?
# Tune/optimize the chosen model for the best performance
# Ensuring the trained model will generalize to unseen data
# Estimate performance of the trained model on unseen data

# imports
import sklearn
import IPython.display
import matplotlib.pyplot as plt

jainxy

Let machine M be the Main machine with the repo, and A the Auxiliary machine which wants to help out.

First time setup

1. Machine M creates bundle with complete repo:

git bundle create repo.bundle HEAD master

2. M sends repo.bundle to A.
3. A clones repo from bundle:

jainxy

References - 
1. https://www.howtoforge.com/tutorial/how-to-create-docker-images-with-dockerfile/
2. https://takacsmark.com/dockerfile-tutorial-by-example-dockerfile-best-practices-2018/
3. https://docs.docker.com/engine/reference/builder/
Notes - 
 - A script or receipe having collection of commands and instructions, which will be executed in sequence, to build a new docker image.
 - Below are some Dockerfile commands and their usage.

1. FROM
 - Base docker image to build new image on top. This is 1st command in the Dockerfile. E.g. dockerized ubuntu image.

jainxy

from concurrent.futures import ProcessPoolExecutor, as_completed
import cv2
import multiprocessing
import os
import sys


def print_progress(iteration, total, prefix='', suffix='', decimals=3, bar_length=100):
    """
    Call in a loop to create standard out progress bar

jainxy

import cv2  # still used to save images out
import os
import numpy as np
from decord import VideoReader
from decord import cpu, gpu


def extract_frames(video_path, frames_dir, overwrite=False, start=-1, end=-1, every=1):
    """
    Extract frames from a video using decord's VideoReader