viralbthakar

import tensorflow as tf
from tensorflow.keras import layers, models
from tensorflow.keras.datasets import cifar10
import time

# Load CIFAR-10 dataset
(train_images, train_labels), (test_images, test_labels) = cifar10.load_data()

# Normalize pixel values to be between 0 and 1
train_images, test_images = train_images / 255.0, test_images / 255.0

viralbthakar

import io
import os
import tqdm
import argparse
import numpy as np
import pandas as pd
import tensorflow as tf
from utils import styled_print
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

viralbthakar

{
  "embeddings": [
    {
      "tensorName": "Fire and Blood - Word2Vec",
      "tensorShape": [
        300,
        13693
      ],
      "tensorPath": "https://gist.githubusercontent.com/viralbthakar/b2d318565ae4a628dbecba6ee39fbf11/raw/4441c894b9d52797ee2cef9b6c914b57f7ef2cda/vectors.tsv",
      "metadataPath": "https://gist.githubusercontent.com/viralbthakar/2c3c8469931b07a36ffe05f3ba0128f6/raw/12c18b0763866f6a177959514892f269e45d0f63/metadata.tsv"

viralbthakar

-0.048866298	-0.0016785637	0.0038877502	0.0040101036	0.033698905	0.022059526	0.027706925	-0.03167452	0.02778678	-0.022080792	0.043521475	-0.0018232353	-0.0047206506	0.022144224	0.04939803	0.022760537	-0.008644424	-0.016616572	0.0220027	-0.026030077	-0.020085013	-0.035149373	-0.046827864	0.011195052	0.020963196	0.00949068	0.034231115	-0.037880994	-0.0024146214	-0.031831015	0.013744149	-0.021530164	-0.03460578	0.0068220496	-0.026724327	-0.03672732	0.0036778934	0.02596232	-0.008625388	-0.026180243	0.030728605	-0.033938088	0.01160755	0.008664608	0.044776943	0.044101965	-0.042550564	0.04983506	-0.023614382	0.009385873	0.045363855	0.00018430874	0.008923959	0.019788656	0.0208782	-0.008075904	0.014386807	-0.0077568777	0.03852633	0.030512046	-0.013017915	0.014862601	0.006768964	0.03516427	0.0016545281	0.04538654	-0.043342542	0.04143813	-0.02258116	-0.016876448	-0.035590887	0.019355956	-0.04687668	0.014895808	-0.031816438	0.02420688	0.000644695	-0.020795071	0.045877267	0.022969197	0.03598148	-0.046948362	0.0031965002	-

viralbthakar

[UNK]
’
“
”
The
Lord
Rhaenyra
would
King
Ser

viralbthakar

import os
import random
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow.keras.layers import Input, Convolution2D, MaxPooling2D, Activation, Dense, Flatten
from tensorflow.keras.models import Model

#Set The Parametes
DATA_DIR = "./data"

viralbthakar

def get_model_arch(input_shape, last_layer_nodes=1000, last_layer_activation='sigmoid'):
	input_img = Input(input_shape, name='input')
	x = Convolution2D(64, (3, 3), activation='relu', padding='same', name='fe0_conv1')(input_img)
	x = Convolution2D(64, (3, 3), activation='relu', padding='same', name='fe0_conv2')(x)
	x = MaxPooling2D((2, 2), padding='same', name='fe0_mp')(x)

	x = Convolution2D(128, (3, 3), activation='relu', padding='same', name='fe1_conv1')(x)
	x = Convolution2D(128, (3, 3), activation='relu', padding='same', name='fe1_conv2')(x)
	x = MaxPooling2D((2, 2), padding='same', name='fe1_mp')(x)
	

viralbthakar

import tensorflow as tf

def get_img_file(img_path, input_shape):
	image = tf.io.read_file(img_path)
	image = tf.image.decode_jpeg(image, channels=3)
	image = tf.image.resize(image, [input_shape[0], input_shape[1]], antialias=True)
	image = tf.cast(image, tf.float32)/255.0
	return image

def parse_function(ip_dict, input_shape):

viralbthakar

def get_per_class_image_list(image_dir, image_list, class_name, split_iden=".", split_iden_index=0, shuffle=True):
	class_name_image_list = [os.path.join(image_dir, image_file) for image_file in image_list if image_file.split(split_iden)[split_iden_index] == class_name]
	if shuffle:
		random.shuffle(class_name_image_list)
	print("For Class {} Found {} Images".format(class_name, len(class_name_image_list)))
	return class_name_image_list

def split_data(image_dir, image_list, class_list, split_index):
	train_data_dict = {"images":[], "labels":[]}
	val_data_dict = {"images":[], "labels":[]}