kbrajwani

#!/bin/python3

import math
import os
import random
import re
import sys

# Complete the reverseShuffleMerge function below.

kbrajwani

read 

https://colab.research.google.com/drive/1tGgypw1qM6TJD9A2NLWI_X1JMoyiuC_b
https://github.com/dair-ai/nlp_paper_summaries

model compiler like tvm

http://montreal.ai/ai4all.pdf
book Statistics for Data Science James D. Miller [James D. Miller]
book approching almost any machine learning problem

kbrajwani

Three major task
1. Parser
	Preprocess the text
	research different algorithms	
	extract keyword of interest	
2. Matcher
	Preprocess the text
	research different algorithms	
	evaluate algorithm and choose best to match
3. Rest api

kbrajwani

https://www.kaggle.com/bamps53/private0-9704-tpu-keras-metric-learning/data
https://www.kaggle.com/c/bengaliai-cv19/discussion/136030
https://www.kaggle.com/c/bengaliai-cv19/discussion/136815
https://www.kaggle.com/c/bengaliai-cv19/discussion/135984
https://www.kaggle.com/haqishen/notebooks
https://www.kaggle.com/haqishen/train-efficientnet-b0-w-36-tiles-256-lb0-87
https://www.kaggle.com/c/humpback-whale-identification/discussion/82366
https://www.kaggle.com/c/humpback-whale-identification/discussion/82352
https://www.kaggle.com/nroman/melanoma-pytorch-starter-efficientnet
https://www.kaggle.com/iafoss/panda-concat-tile-pooling-starter-0-79-lb

kbrajwani

--------------------------------------metric explain-----------------------------
A great metric that should always be used when dealing with the classification problem is the confusion matrix.

The accuracy of the model is basically the total number of correct predictions divided by the total number of predictions.

The precision of a class defines how trustable is the result when the model answers that a point belongs to that class.

The recall of a class expresses how well the model is able to detect that class.

The F1 score of a class is given by the harmonic mean of precision and recall (2×precision×recall / (precision + recall)), it combines precision and recall of a class in one metric.

kbrajwani

https://towardsdatascience.com/distilling-bert-how-to-achieve-bert-performance-using-logistic-regression-69a7fc14249d

https://towardsdatascience.com/knowledge-distillation-and-the-concept-of-dark-knowledge-8b7aed8014ac

https://blog.floydhub.com/knowledge-distillation/

kbrajwani

Sathyajith Bhat - Practical Docker with Python_ Build, Release and Distribute Your Python App with

https://augmentedstartups.com/category/artificial-intelligence/

https://yanjia.li/dive-really-deep-into-yolo-v3-a-beginners-guide/

https://towardsdatascience.com/knowledge-distillation-and-the-concept-of-dark-knowledge-8b7aed8014ac

https://towardsdatascience.com/3-steps-to-update-parameters-of-faster-r-cnn-ssd-models-in-tensorflow-object-detection-api-7eddb11273ed

kbrajwani

language: en
pipeline:
- name: entity_mapping.SpellChecker
- name: nlp_spacy
  model: en_core_web_md
  case_sensitive: false
- name: tokenizer_spacy
- name: ner_crf
- name: intent_featurizer_spacy
- name: intent_classifier_sklearn

kbrajwani

from django.contrib import admin
from django.urls import path
from . import views
urlpatterns = [
    path('', views.index, name='homepage'),
    path('admin/', admin.site.urls),
]

kbrajwani

<form method="post" enctype="multipart/form-data">
    {% csrf_token %}
    <input type="file" name="sentFile" />
    <input type="submit" name="submit" value="Upload" />
</form>
{{name}}