piEsposito

package main

import (
	"fmt"
	"time"
)

func feedChannel(c chan int) {
	//aqui vamos feedar nosso canal
	for i := 0; i < 10; i++ {

piEsposito

package main

import (
	"fmt"
	"sync"
)

func feedChannel(c chan int, wg *sync.WaitGroup) {
	//aqui vamos feedar nosso canal
	for i := 0; i < 10; i++ {

piEsposito

package main

import (
	"fmt"
	"sync"
	"time"
	"webmotor_crawler/crawl_functions"
)

func main() {

piEsposito

package crawl_functions

import (
	"fmt"
	"strconv"
	"sync"
)

func FeedChannel(page_start int, page_nmr int, c chan int, wg *sync.WaitGroup) {
	/*

piEsposito

package crawl_functions

import (
	"fmt"
	"sync"
	"webmotor_crawler/query_handler"
)

func CrawlRoutine(wg *sync.WaitGroup, c chan int) {
	/*

piEsposito

package query_handler

import (
	"net/http"
	"net/url"

	"golang.org/x/net/proxy"
)

type QueryClient struct {

piEsposito

package query_handler

import (
	"compress/gzip"
	"fmt"
	"io/ioutil"
	"net/http"
	"os"
)

piEsposito

import torch
from torch import nn
from blitz.modules import BayesianLinear

class BayesianRegressor(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
        self.blinear1 = BayesianLinear(input_dim, 64)
        self.blinear2 = BayesianLinear(64, output_dim)

piEsposito

@variational_estimator
class BayesianRegressor(nn.Module):
    def __init__(self,):
        super().__init__()
        #self.linear = nn.Linear(input_dim, output_dim)
        self.blinear1 = BayesianLinear(input_dim, 512)
        self.blinear2 = BayesianLinear(512, output_dim)
        
    def forward(self, x):
        x_ = self.blinear1(x)

piEsposito

iteration = 0
for epoch in range(100):
    for i, (datapoints, labels) in enumerate(dataloader_train):
        optimizer.zero_grad()
        
        loss = regressor.sample_elbo(inputs=datapoints,
                           labels=labels,
                           criterion=criterion,
                           sample_nbr=3)
        loss.backward()