sgsg704

model.save('pet.h5')

sgsg704

scores = model.evaluate(valx, valy, verbose=0)
print("{}: {:.2f}%".format("accuracy", scores[1]*100))

model.summary()

sgsg704

 model.fit(testx,testy,validation_data =(valx,valy),batch_size=750,epochs=256,callbacks = [callback])

sgsg704

from tensorflow.keras.models import Sequential
model  = Sequential()
trainX.shape


model.add(Dense(4096,activation= 'relu',input_shape=(16,))) #dense layer 1
model.add(tf.keras.layers.BatchNormalization()) #BachNorm
model.add(tf.keras.layers.Dropout(0.25)) #Dropout
model.add(Dense(2048,activation= 'relu'))
model.add(tf.keras.layers.Dropout(0.25)) #Dropout

sgsg704

for col in trainX.columns:
    if trainX[col].dtype=='object':
        trainX.drop([col],axis=1,inplace=True)
for col in test.columns:
    if test[col].dtype=='object':
        test.drop([col],axis=1,inplace=True)
        
        
        
trainY = pd.DataFrame()

sgsg704

for col in trainX.columns:
    if trainX[col].dtype=='object':
        trainX.drop([col],axis=1,inplace=True)

sgsg704

trainX = pd.read_csv('https://cainvas-static.s3.amazonaws.com/media/user_data/hrithikgupta/train_pet.csv')
test = pd.read_csv('https://cainvas-static.s3.amazonaws.com/media/user_data/hrithikgupta/test_pet.csv')
print(trainX.shape)
print(test.shape)
trainX.head()

sgsg704

import tensorflow as tf
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
import cv2
import os
from tensorflow.keras.layers import Dense,BatchNormalization
from sklearn.model_selection import train_test_split

sgsg704

import pickle

filename = 'finalized_model.sav'
pickle.dump(MLP, open(filename, 'wb'))

sgsg704

MLP = MLPRegressor(activation='relu', alpha=10, batch_size='auto', beta_1=0.9,
       beta_2=0.999, early_stopping=False, epsilon=1e-08,
       hidden_layer_sizes=(100,), learning_rate='constant',
       learning_rate_init=0.001, max_iter=500, momentum=0.9,
       nesterovs_momentum=True, power_t=0.5, random_state=None,
       shuffle=True, solver='adam', tol=0.0001, validation_fraction=0.1,
       verbose=False, warm_start=False)
       
       
       # scores