Add new Experiments, with noise addition and better save
This commit is contained in:
parent
c900129ec9
commit
b62011c029
GPG Key ID:
941DF56C7242C3F1
|
|
@ -1,8 +1,9 @@
|
|||
import pickle
|
||||
from warnings import warn
|
||||
|
||||
from gpu_power_func import get_sample_of_gpu
|
||||
|
||||
with (open("configuration.pkl", "rb")) as file:
|
||||
with open("configuration.pkl", "rb") as file:
|
||||
while True:
|
||||
try:
|
||||
cfg = pickle.load(file)
|
||||
|
|
@ -16,14 +17,14 @@ with (open("configuration.pkl", "rb")) as file:
|
|||
# print(cfg)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if __name__ == "__main__":
|
||||
dataDump = []
|
||||
while True:
|
||||
try:
|
||||
dataDump.append(get_sample_of_gpu())
|
||||
with open(cfg["pickle_path"], 'wb') as f:
|
||||
with open(cfg["pickle_path"], "wb") as f:
|
||||
pickle.dump(dataDump, f)
|
||||
except EOFError:
|
||||
warn('Pickle ran out of space')
|
||||
warn("Pickle ran out of space")
|
||||
finally:
|
||||
f.close()
|
||||
|
|
|
|||
56
arguments.py
56
arguments.py
|
|
@ -6,22 +6,42 @@ all_args = argparse.ArgumentParser()
|
|||
|
||||
|
||||
def makeArguments(arguments: ArgumentParser) -> dict:
|
||||
all_args.add_argument("-b", "--Bayesian", action="store", dest="b",
|
||||
type=int, choices=range(1, 8),
|
||||
help="Bayesian model of size x")
|
||||
all_args.add_argument("-f", "--Frequentist", action="store", dest="f",
|
||||
type=int, choices=range(1, 8),
|
||||
help="Frequentist model of size x")
|
||||
all_args.add_argument("-E", "--EarlyStopping", action="store_true",
|
||||
help="Early Stopping criteria")
|
||||
all_args.add_argument("-e", "--EnergyBound", action="store_true",
|
||||
help="Energy Bound criteria")
|
||||
all_args.add_argument("-a", "--AccuracyBound", action="store_true",
|
||||
help="Accuracy Bound criteria")
|
||||
all_args.add_argument("-s", "--Save", action="store_true",
|
||||
help="Save model")
|
||||
all_args.add_argument('--net_type', default='lenet', type=str,
|
||||
help='model = [lenet/AlexNet/3Conv3FC]')
|
||||
all_args.add_argument('--dataset', default='CIFAR10', type=str,
|
||||
help='dataset = [MNIST/CIFAR10/CIFAR100]')
|
||||
"""Training arguments to be passed to the model"""
|
||||
all_args.add_argument(
|
||||
"-b",
|
||||
"--Bayesian",
|
||||
action="store",
|
||||
dest="b",
|
||||
type=int,
|
||||
choices=range(1, 8),
|
||||
help="Bayesian model of size x",
|
||||
)
|
||||
all_args.add_argument(
|
||||
"-f",
|
||||
"--Frequentist",
|
||||
action="store",
|
||||
dest="f",
|
||||
type=int,
|
||||
choices=range(1, 8),
|
||||
help="Frequentist model of size x",
|
||||
)
|
||||
all_args.add_argument(
|
||||
"-E", "--EarlyStopping", action="store_true", help="Early Stopping criteria"
|
||||
)
|
||||
all_args.add_argument(
|
||||
"-e", "--EnergyBound", action="store_true", help="Energy Bound criteria"
|
||||
)
|
||||
all_args.add_argument(
|
||||
"-a", "--AccuracyBound", action="store_true", help="Accuracy Bound criteria"
|
||||
)
|
||||
all_args.add_argument("-s", "--Save", action="store_true", help="Save model")
|
||||
all_args.add_argument(
|
||||
"--net_type", default="lenet", type=str, help="model = [lenet/AlexNet/3Conv3FC]"
|
||||
)
|
||||
all_args.add_argument(
|
||||
"--dataset",
|
||||
default="CIFAR10",
|
||||
type=str,
|
||||
help="dataset = [MNIST/CIFAR10/CIFAR100]",
|
||||
)
|
||||
return vars(all_args.parse_args())
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
#!/bin/env bash
|
||||
#!/usr/bin/env bash
|
||||
|
||||
powerstat -D -z 0.5 10000000 > $1
|
||||
#powerstat -z 0.5 1000000 > $1
|
||||
|
|
|
|||
|
|
@ -1,18 +1,20 @@
|
|||
import os
|
||||
import re
|
||||
import pickle
|
||||
import re
|
||||
import subprocess
|
||||
from re import findall, sub
|
||||
from subprocess import run
|
||||
|
||||
import numpy as np
|
||||
|
||||
|
||||
def get_sample_of_gpu():
|
||||
from re import sub, findall
|
||||
import subprocess
|
||||
from subprocess import run
|
||||
|
||||
no_graph = "NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the latest NVIDIA driver is installed and running."
|
||||
no_version = "Failed to initialize NVML: Driver/library version mismatch"
|
||||
smi_string = run(['rocm-smi', '-P', '--showvoltage', '--showmemuse'], stdout=subprocess.PIPE)
|
||||
smi_string = smi_string.stdout.decode('utf-8')
|
||||
smi_string = run(
|
||||
["rocm-smi", "-P", "--showvoltage", "--showmemuse"], stdout=subprocess.PIPE
|
||||
)
|
||||
smi_string = smi_string.stdout.decode("utf-8")
|
||||
smi_string = smi_string.split("\n")
|
||||
smi_string = list(filter(lambda x: x, smi_string))
|
||||
if smi_string[0] == no_graph:
|
||||
|
|
@ -20,13 +22,13 @@ def get_sample_of_gpu():
|
|||
elif smi_string[0] == no_version:
|
||||
raise Exception("rocm-smi version mismatch")
|
||||
else:
|
||||
results= []
|
||||
gpuW0 = findall("[0-9]*\.[0-9]*",smi_string[2])
|
||||
gpuW1 = findall("[0-9]*\.[0-9]*",smi_string[4])
|
||||
gpuM0 = findall("[0-9]+",smi_string[7])
|
||||
gpuM1 = findall("[0-9]+",smi_string[9])
|
||||
gpuV0 = findall("[0-9]+",smi_string[13])
|
||||
gpuV1 = findall("[0-9]+",smi_string[14])
|
||||
results = []
|
||||
gpuW0 = findall(r"[0-9]*\.[0-9]*", smi_string[2])
|
||||
gpuW1 = findall(r"[0-9]*\.[0-9]*", smi_string[3])
|
||||
gpuM0 = findall(r"[0-9]+", smi_string[6])
|
||||
gpuM1 = findall(r"[0-9]+", smi_string[10])
|
||||
gpuV0 = findall(r"[0-9]+", smi_string[16])
|
||||
gpuV1 = findall(r"[0-9]+", smi_string[17])
|
||||
results.append(float(gpuW0[0]) + float(gpuW1[0]))
|
||||
if len(gpuM0) == 2 and len(gpuM1) == 2:
|
||||
results.append(int(gpuM0[1]) + int(gpuM1[1]))
|
||||
|
|
@ -36,19 +38,21 @@ def get_sample_of_gpu():
|
|||
results.append(gpuM1[1])
|
||||
results.append(int(gpuV0[1]) + int(gpuV1[1]))
|
||||
return results
|
||||
#for l in smi_string:
|
||||
#temp = findall("[0-9]*MiB | [0-9]*W",l)
|
||||
#if temp:
|
||||
#return temp
|
||||
# for l in smi_string:
|
||||
# temp = findall("[0-9]*MiB | [0-9]*W",l)
|
||||
# if temp:
|
||||
# return temp
|
||||
|
||||
|
||||
def total_watt_consumed(pickle_name):
|
||||
with (open(pickle_name, "rb")) as file:
|
||||
with open(pickle_name, "rb") as file:
|
||||
while True:
|
||||
try:
|
||||
x = pickle.load(file)
|
||||
except EOFError:
|
||||
break
|
||||
x = np.array(x)
|
||||
x = x[:,0]
|
||||
y = [float(re.findall("\d+.\d+",xi)[0]) for xi in x]
|
||||
x = x[:, 0]
|
||||
y = [float(re.findall("\d+.\d+", xi)[0]) for xi in x]
|
||||
return sum(y)
|
||||
|
||||
|
|
|
|||
145
main_bayesian.py
145
main_bayesian.py
|
|
@ -1,21 +1,23 @@
|
|||
from __future__ import print_function
|
||||
|
||||
import os
|
||||
import data
|
||||
import utils
|
||||
import torch
|
||||
import pickle
|
||||
import metrics
|
||||
import numpy as np
|
||||
from datetime import datetime
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch.nn import functional as F
|
||||
from torch.optim import Adam, lr_scheduler
|
||||
from models.BayesianModels.BayesianLeNet import BBBLeNet
|
||||
from models.BayesianModels.BayesianAlexNet import BBBAlexNet
|
||||
from models.BayesianModels.Bayesian3Conv3FC import BBB3Conv3FC
|
||||
from stopping_crit import earlyStopping, energyBound, accuracyBound
|
||||
|
||||
with (open("configuration.pkl", "rb")) as file:
|
||||
import data
|
||||
import metrics
|
||||
import utils
|
||||
from models.BayesianModels.Bayesian3Conv3FC import BBB3Conv3FC
|
||||
from models.BayesianModels.BayesianAlexNet import BBBAlexNet
|
||||
from models.BayesianModels.BayesianLeNet import BBBLeNet
|
||||
from stopping_crit import accuracy_bound, e_stop, energy_bound
|
||||
|
||||
with open("configuration.pkl", "rb") as file:
|
||||
while True:
|
||||
try:
|
||||
cfg = pickle.load(file)
|
||||
|
|
@ -28,21 +30,37 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
|
|||
|
||||
|
||||
def getModel(net_type, inputs, outputs, priors, layer_type, activation_type):
|
||||
if (net_type == 'lenet'):
|
||||
return BBBLeNet(outputs, inputs, priors, layer_type, activation_type,
|
||||
wide=cfg["model"]["size"])
|
||||
elif (net_type == 'alexnet'):
|
||||
print(net_type)
|
||||
if net_type == "lenet":
|
||||
return BBBLeNet(
|
||||
outputs,
|
||||
inputs,
|
||||
priors,
|
||||
layer_type,
|
||||
activation_type,
|
||||
wide=cfg["model"]["size"],
|
||||
)
|
||||
elif net_type == "alexnet":
|
||||
return BBBAlexNet(outputs, inputs, priors, layer_type, activation_type)
|
||||
elif (net_type == '3conv3fc'):
|
||||
return BBB3Conv3FC(outputs, inputs, priors, layer_type,
|
||||
activation_type)
|
||||
elif net_type == "3conv3fc":
|
||||
return BBB3Conv3FC(outputs, inputs, priors, layer_type, activation_type)
|
||||
else:
|
||||
raise ValueError('Network should be either [LeNet / AlexNet\
|
||||
/ 3Conv3FC')
|
||||
raise ValueError(
|
||||
"Network should be either [LeNet / AlexNet\
|
||||
/ 3Conv3FC"
|
||||
)
|
||||
|
||||
|
||||
def train_model(net, optimizer, criterion, trainloader, num_ens=1,
|
||||
beta_type=0.1, epoch=None, num_epochs=None):
|
||||
def train_model(
|
||||
net,
|
||||
optimizer,
|
||||
criterion,
|
||||
trainloader,
|
||||
num_ens=1,
|
||||
beta_type=0.1,
|
||||
epoch=None,
|
||||
num_epochs=None,
|
||||
):
|
||||
net.train()
|
||||
training_loss = 0.0
|
||||
accs = []
|
||||
|
|
@ -52,8 +70,7 @@ def train_model(net, optimizer, criterion, trainloader, num_ens=1,
|
|||
optimizer.zero_grad()
|
||||
|
||||
inputs, labels = inputs.to(device), labels.to(device)
|
||||
outputs = torch.zeros(inputs.shape[0], net.num_classes,
|
||||
num_ens).to(device)
|
||||
outputs = torch.zeros(inputs.shape[0], net.num_classes, num_ens).to(device)
|
||||
|
||||
kl = 0.0
|
||||
for j in range(num_ens):
|
||||
|
|
@ -65,19 +82,19 @@ def train_model(net, optimizer, criterion, trainloader, num_ens=1,
|
|||
kl_list.append(kl.item())
|
||||
log_outputs = utils.logmeanexp(outputs, dim=2)
|
||||
|
||||
beta = metrics.get_beta(i-1, len(trainloader), beta_type,
|
||||
epoch, num_epochs)
|
||||
beta = metrics.get_beta(i - 1, len(trainloader), beta_type, epoch, num_epochs)
|
||||
loss = criterion(log_outputs, labels, kl, beta)
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
accs.append(metrics.acc(log_outputs.data, labels))
|
||||
training_loss += loss.cpu().data.numpy()
|
||||
return training_loss/len(trainloader), np.mean(accs), np.mean(kl_list)
|
||||
return training_loss / len(trainloader), np.mean(accs), np.mean(kl_list)
|
||||
|
||||
|
||||
def validate_model(net, criterion, validloader, num_ens=1, beta_type=0.1,
|
||||
epoch=None, num_epochs=None):
|
||||
def validate_model(
|
||||
net, criterion, validloader, num_ens=1, beta_type=0.1, epoch=None, num_epochs=None
|
||||
):
|
||||
"""Calculate ensemble accuracy and NLL Loss"""
|
||||
net.train()
|
||||
valid_loss = 0.0
|
||||
|
|
@ -85,8 +102,7 @@ def validate_model(net, criterion, validloader, num_ens=1, beta_type=0.1,
|
|||
|
||||
for i, (inputs, labels) in enumerate(validloader):
|
||||
inputs, labels = inputs.to(device), labels.to(device)
|
||||
outputs = torch.zeros(inputs.shape[0], net.num_classes,
|
||||
num_ens).to(device)
|
||||
outputs = torch.zeros(inputs.shape[0], net.num_classes, num_ens).to(device)
|
||||
kl = 0.0
|
||||
for j in range(num_ens):
|
||||
net_out, _kl = net(inputs)
|
||||
|
|
@ -95,12 +111,11 @@ def validate_model(net, criterion, validloader, num_ens=1, beta_type=0.1,
|
|||
|
||||
log_outputs = utils.logmeanexp(outputs, dim=2)
|
||||
|
||||
beta = metrics.get_beta(i-1, len(validloader), beta_type,
|
||||
epoch, num_epochs)
|
||||
beta = metrics.get_beta(i - 1, len(validloader), beta_type, epoch, num_epochs)
|
||||
valid_loss += criterion(log_outputs, labels, kl, beta).item()
|
||||
accs.append(metrics.acc(log_outputs, labels))
|
||||
|
||||
return valid_loss/len(validloader), np.mean(accs)
|
||||
return valid_loss / len(validloader), np.mean(accs)
|
||||
|
||||
|
||||
def run(dataset, net_type):
|
||||
|
|
@ -121,11 +136,13 @@ def run(dataset, net_type):
|
|||
|
||||
trainset, testset, inputs, outputs = data.getDataset(dataset)
|
||||
train_loader, valid_loader, test_loader = data.getDataloader(
|
||||
trainset, testset, valid_size, batch_size, num_workers)
|
||||
net = getModel(net_type, inputs, outputs, priors, layer_type,
|
||||
activation_type).to(device)
|
||||
trainset, testset, valid_size, batch_size, num_workers
|
||||
)
|
||||
net = getModel(net_type, inputs, outputs, priors, layer_type, activation_type).to(
|
||||
device
|
||||
)
|
||||
|
||||
ckpt_dir = f'checkpoints/{dataset}/bayesian'
|
||||
ckpt_dir = f"checkpoints/{dataset}/bayesian"
|
||||
ckpt_name = f'checkpoints/{dataset}/bayesian/model_{net_type}_{layer_type}\
|
||||
_{activation_type}_{cfg["model"]["size"]}.pt'
|
||||
|
||||
|
|
@ -137,66 +154,72 @@ def run(dataset, net_type):
|
|||
|
||||
criterion = metrics.ELBO(len(trainset)).to(device)
|
||||
optimizer = Adam(net.parameters(), lr=lr_start)
|
||||
lr_sched = lr_scheduler.ReduceLROnPlateau(optimizer, patience=6,
|
||||
verbose=True)
|
||||
lr_sched = lr_scheduler.ReduceLROnPlateau(optimizer, patience=6, verbose=True)
|
||||
# valid_loss_max = np.Inf
|
||||
# if stp == 2:
|
||||
early_stop = []
|
||||
train_data = []
|
||||
for epoch in range(n_epochs): # loop over the dataset multiple times
|
||||
|
||||
train_loss, train_acc, train_kl = train_model(net, optimizer,
|
||||
train_loss, train_acc, train_kl = train_model(
|
||||
net,
|
||||
optimizer,
|
||||
criterion,
|
||||
train_loader,
|
||||
num_ens=train_ens,
|
||||
beta_type=beta_type,
|
||||
epoch=epoch,
|
||||
num_epochs=n_epochs)
|
||||
valid_loss, valid_acc = validate_model(net, criterion, valid_loader,
|
||||
num_epochs=n_epochs,
|
||||
)
|
||||
valid_loss, valid_acc = validate_model(
|
||||
net,
|
||||
criterion,
|
||||
valid_loader,
|
||||
num_ens=valid_ens,
|
||||
beta_type=beta_type,
|
||||
epoch=epoch,
|
||||
num_epochs=n_epochs)
|
||||
num_epochs=n_epochs,
|
||||
)
|
||||
lr_sched.step(valid_loss)
|
||||
|
||||
train_data.append([epoch, train_loss, train_acc, valid_loss,
|
||||
valid_acc])
|
||||
print('Epoch: {} \tTraining Loss: {:.4f} \tTraining Accuracy:\
|
||||
train_data.append([epoch, train_loss, train_acc, valid_loss, valid_acc])
|
||||
print(
|
||||
"Epoch: {} \tTraining Loss: {:.4f} \tTraining Accuracy:\
|
||||
{:.4f} \tValidation Loss: {:.4f} \tValidation Accuracy:\
|
||||
{:.4f} \ttrain_kl_div: {:.4f}'.format(epoch, train_loss,
|
||||
train_acc, valid_loss,
|
||||
valid_acc, train_kl))
|
||||
{:.4f} \ttrain_kl_div: {:.4f}".format(
|
||||
epoch, train_loss, train_acc, valid_loss, valid_acc, train_kl
|
||||
)
|
||||
)
|
||||
|
||||
if stp == 2:
|
||||
print('Using early stopping')
|
||||
if earlyStopping(early_stop, valid_acc, epoch,
|
||||
cfg["model"]["sens"]) == 1:
|
||||
# print("Using early stopping")
|
||||
if e_stop(early_stop, valid_acc, epoch + 1, 2, cfg["model"]["sens"]) == 1:
|
||||
break
|
||||
elif stp == 3:
|
||||
print('Using energy bound')
|
||||
if energyBound(cfg["model"]["energy_thrs"]) == 1:
|
||||
# print("Using energy bound")
|
||||
if energy_bound(cfg["model"]["energy_thrs"]) == 1:
|
||||
break
|
||||
elif stp == 4:
|
||||
print('Using accuracy bound')
|
||||
if accuracyBound(train_acc, cfg.acc_thrs) == 1:
|
||||
# print("Using accuracy bound")
|
||||
if accuracy_bound(train_acc, cfg.acc_thrs) == 1:
|
||||
break
|
||||
else:
|
||||
print('Training for {} epochs'.format(cfg["model"]["n_epochs"]))
|
||||
print("Training for {} epochs".format(cfg["model"]["n_epochs"]))
|
||||
|
||||
if sav == 1:
|
||||
# save model when finished
|
||||
if epoch == cfg.n_epochs-1:
|
||||
if epoch == cfg.n_epochs - 1:
|
||||
torch.save(net.state_dict(), ckpt_name)
|
||||
|
||||
with open("bayes_exp_data_"+str(cfg["model"]["size"])+".pkl", 'wb') as f:
|
||||
with open("bayes_exp_data_" + str(cfg["model"]["size"]) + ".pkl", "wb") as f:
|
||||
pickle.dump(train_data, f)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if __name__ == "__main__":
|
||||
now = datetime.now()
|
||||
current_time = now.strftime("%H:%M:%S")
|
||||
print("Initial Time =", current_time)
|
||||
print("Using bayesian model of size: {}".format(cfg["model"]["size"]))
|
||||
print(f"Using bayesian model of size: {cfg["model"]["size"]}")
|
||||
run(cfg["data"], cfg["model"]["net_type"])
|
||||
now = datetime.now()
|
||||
current_time = now.strftime("%H:%M:%S")
|
||||
|
|
|
|||
|
|
@ -1,19 +1,22 @@
|
|||
from __future__ import print_function
|
||||
import os
|
||||
import data
|
||||
import torch
|
||||
import pickle
|
||||
import metrics
|
||||
import numpy as np
|
||||
import torch.nn as nn
|
||||
from datetime import datetime
|
||||
from torch.optim import Adam, lr_scheduler
|
||||
from models.NonBayesianModels.LeNet import LeNet
|
||||
from models.NonBayesianModels.AlexNet import AlexNet
|
||||
from stopping_crit import earlyStopping, energyBound, accuracyBound
|
||||
from models.NonBayesianModels.ThreeConvThreeFC import ThreeConvThreeFC
|
||||
|
||||
with (open("configuration.pkl", "rb")) as file:
|
||||
import os
|
||||
import pickle
|
||||
from datetime import datetime
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.optim import Adam, lr_scheduler
|
||||
|
||||
import data
|
||||
import metrics
|
||||
from models.NonBayesianModels.AlexNet import AlexNet
|
||||
from models.NonBayesianModels.LeNet import LeNet
|
||||
from models.NonBayesianModels.ThreeConvThreeFC import ThreeConvThreeFC
|
||||
from stopping_crit import accuracy_bound, e_stop, energy_bound
|
||||
|
||||
with open("configuration.pkl", "rb") as file:
|
||||
while True:
|
||||
try:
|
||||
cfg = pickle.load(file)
|
||||
|
|
@ -25,15 +28,17 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
|
|||
|
||||
|
||||
def getModel(net_type, inputs, outputs, wide=cfg["model"]["size"]):
|
||||
if (net_type == 'lenet'):
|
||||
if net_type == "lenet":
|
||||
return LeNet(outputs, inputs, wide)
|
||||
elif (net_type == 'alexnet'):
|
||||
elif net_type == "alexnet":
|
||||
return AlexNet(outputs, inputs)
|
||||
elif (net_type == '3conv3fc'):
|
||||
elif net_type == "3conv3fc":
|
||||
return ThreeConvThreeFC(outputs, inputs)
|
||||
else:
|
||||
raise ValueError('Network should be either [LeNet / AlexNet / \
|
||||
3Conv3FC')
|
||||
raise ValueError(
|
||||
"Network should be either [LeNet / AlexNet / \
|
||||
3Conv3FC"
|
||||
)
|
||||
|
||||
|
||||
def train_model(net, optimizer, criterion, train_loader):
|
||||
|
|
@ -47,7 +52,7 @@ def train_model(net, optimizer, criterion, train_loader):
|
|||
loss = criterion(output, target)
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
train_loss += loss.item()*data.size(0)
|
||||
train_loss += loss.item() * data.size(0)
|
||||
accs.append(metrics.acc(output.detach(), target))
|
||||
return train_loss, np.mean(accs)
|
||||
|
||||
|
|
@ -60,7 +65,7 @@ def validate_model(net, criterion, valid_loader):
|
|||
data, target = datas.to(device), target.to(device)
|
||||
output = net(data)
|
||||
loss = criterion(output, target)
|
||||
valid_loss += loss.item()*data.size(0)
|
||||
valid_loss += loss.item() * data.size(0)
|
||||
accs.append(metrics.acc(output.detach(), target))
|
||||
return valid_loss, np.mean(accs)
|
||||
|
||||
|
|
@ -76,10 +81,11 @@ def run(dataset, net_type):
|
|||
|
||||
trainset, testset, inputs, outputs = data.getDataset(dataset)
|
||||
train_loader, valid_loader, test_loader = data.getDataloader(
|
||||
trainset, testset, valid_size, batch_size, num_workers)
|
||||
trainset, testset, valid_size, batch_size, num_workers
|
||||
)
|
||||
net = getModel(net_type, inputs, outputs).to(device)
|
||||
|
||||
ckpt_dir = f'checkpoints/{dataset}/frequentist'
|
||||
ckpt_dir = f"checkpoints/{dataset}/frequentist"
|
||||
ckpt_name = f'checkpoints/{dataset}/frequentist/model\
|
||||
_{net_type}_{cfg["model"]["size"]}.pt'
|
||||
|
||||
|
|
@ -91,55 +97,54 @@ def run(dataset, net_type):
|
|||
|
||||
criterion = nn.CrossEntropyLoss()
|
||||
optimizer = Adam(net.parameters(), lr=lr)
|
||||
lr_sched = lr_scheduler.ReduceLROnPlateau(optimizer, patience=6,
|
||||
verbose=True)
|
||||
lr_sched = lr_scheduler.ReduceLROnPlateau(optimizer, patience=6, verbose=True)
|
||||
# valid_loss_min = np.Inf
|
||||
# if stp == 2:
|
||||
early_stop = []
|
||||
train_data = []
|
||||
for epoch in range(1, n_epochs+1):
|
||||
for epoch in range(1, n_epochs + 1):
|
||||
|
||||
train_loss, train_acc = train_model(net, optimizer, criterion,
|
||||
train_loader)
|
||||
train_loss, train_acc = train_model(net, optimizer, criterion, train_loader)
|
||||
valid_loss, valid_acc = validate_model(net, criterion, valid_loader)
|
||||
lr_sched.step(valid_loss)
|
||||
|
||||
train_loss = train_loss/len(train_loader.dataset)
|
||||
valid_loss = valid_loss/len(valid_loader.dataset)
|
||||
train_loss = train_loss / len(train_loader.dataset)
|
||||
valid_loss = valid_loss / len(valid_loader.dataset)
|
||||
|
||||
train_data.append([epoch, train_loss, train_acc, valid_loss,
|
||||
valid_acc])
|
||||
print('Epoch: {} \tTraining Loss: {: .4f} \tTraining Accuracy: {: .4f}\
|
||||
train_data.append([epoch, train_loss, train_acc, valid_loss, valid_acc])
|
||||
print(
|
||||
"Epoch: {} \tTraining Loss: {: .4f} \tTraining Accuracy: {: .4f}\
|
||||
\tValidation Loss: {: .4f} \tValidation Accuracy: {: .4f}\
|
||||
'.format(epoch, train_loss, train_acc, valid_loss, valid_acc))
|
||||
".format(
|
||||
epoch, train_loss, train_acc, valid_loss, valid_acc
|
||||
)
|
||||
)
|
||||
|
||||
if stp == 2:
|
||||
# print('Using early stopping')
|
||||
if earlyStopping(early_stop, valid_acc, epoch,
|
||||
cfg["model"]["sens"]) == 1:
|
||||
# print("Using early stopping")
|
||||
if e_stop(early_stop, valid_acc, epoch, 2, cfg["model"]["sens"]) == 1:
|
||||
break
|
||||
elif stp == 3:
|
||||
# print('Using energy bound')
|
||||
if energyBound(cfg["model"]["energy_thrs"]) == 1:
|
||||
if energy_bound(cfg["model"]["energy_thrs"]) == 1:
|
||||
break
|
||||
elif stp == 4:
|
||||
# print('Using accuracy bound')
|
||||
if accuracyBound(train_acc,
|
||||
cfg["model"]["acc_thrs"]) == 1:
|
||||
if accuracy_bound(train_acc, cfg["model"]["acc_thrs"]) == 1:
|
||||
break
|
||||
else:
|
||||
print('Training for {} epochs'.format(cfg["model"]["n_epochs"]))
|
||||
print("Training for {} epochs".format(cfg["model"]["n_epochs"]))
|
||||
|
||||
if sav == 1:
|
||||
# save model when finished
|
||||
if epoch == n_epochs:
|
||||
if epoch <= n_epochs:
|
||||
torch.save(net.state_dict(), ckpt_name)
|
||||
|
||||
with open("freq_exp_data_"+str(cfg["model"]["size"])+".pkl", 'wb') as f:
|
||||
with open("freq_exp_data_" + str(cfg["model"]["size"]) + ".pkl", "wb") as f:
|
||||
pickle.dump(train_data, f)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if __name__ == "__main__":
|
||||
now = datetime.now()
|
||||
current_time = now.strftime("%H:%M:%S")
|
||||
print("Initial Time =", current_time)
|
||||
|
|
|
|||
|
|
@ -1,5 +1,4 @@
|
|||
#!/bin/env bash
|
||||
|
||||
#!/usr/bin/env bash
|
||||
|
||||
while true
|
||||
do
|
||||
|
|
|
|||
|
|
@ -1,8 +1,16 @@
|
|||
import math
|
||||
|
||||
import torch.nn as nn
|
||||
from layers import BBB_Linear, BBB_Conv2d
|
||||
from layers import BBB_LRT_Linear, BBB_LRT_Conv2d
|
||||
from layers import FlattenLayer, ModuleWrapper
|
||||
|
||||
from layers import (
|
||||
BBB_Conv2d,
|
||||
BBB_Linear,
|
||||
BBB_LRT_Conv2d,
|
||||
BBB_LRT_Linear,
|
||||
FlattenLayer,
|
||||
ModuleWrapper,
|
||||
)
|
||||
|
||||
|
||||
class BBB3Conv3FC(ModuleWrapper):
|
||||
"""
|
||||
|
|
@ -10,25 +18,28 @@ class BBB3Conv3FC(ModuleWrapper):
|
|||
Simple Neural Network having 3 Convolution
|
||||
and 3 FC layers with Bayesian layers.
|
||||
"""
|
||||
def __init__(self, outputs, inputs, priors, layer_type='lrt', activation_type='softplus'):
|
||||
|
||||
def __init__(
|
||||
self, outputs, inputs, priors, layer_type="lrt", activation_type="softplus"
|
||||
):
|
||||
super(BBB3Conv3FC, self).__init__()
|
||||
|
||||
self.num_classes = outputs
|
||||
self.layer_type = layer_type
|
||||
self.priors = priors
|
||||
|
||||
if layer_type=='lrt':
|
||||
if layer_type == "lrt":
|
||||
BBBLinear = BBB_LRT_Linear
|
||||
BBBConv2d = BBB_LRT_Conv2d
|
||||
elif layer_type=='bbb':
|
||||
elif layer_type == "bbb":
|
||||
BBBLinear = BBB_Linear
|
||||
BBBConv2d = BBB_Conv2d
|
||||
else:
|
||||
raise ValueError("Undefined layer_type")
|
||||
|
||||
if activation_type=='softplus':
|
||||
if activation_type == "softplus":
|
||||
self.act = nn.Softplus
|
||||
elif activation_type=='relu':
|
||||
elif activation_type == "relu":
|
||||
self.act = nn.ReLU
|
||||
else:
|
||||
raise ValueError("Only softplus or relu supported")
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
#!/bin/env bash
|
||||
#!/usr/bin/env bash
|
||||
|
||||
radeontop -b 08 -d - > $1
|
||||
|
|
|
|||
|
|
@ -1,31 +1,69 @@
|
|||
import pickle
|
||||
from time import sleep
|
||||
|
||||
from gpu_power_func import total_watt_consumed
|
||||
|
||||
with (open("configuration.pkl", "rb")) as file:
|
||||
with open("configuration.pkl", "rb") as file:
|
||||
while True:
|
||||
try:
|
||||
cfg = pickle.load(file)
|
||||
except EOFError:
|
||||
break
|
||||
|
||||
def earlyStopping(early_stopping: list, train_acc: float, epoch: int, sensitivity: float=1e-9):
|
||||
|
||||
def non_decreasing(L):
|
||||
return all(x <= y for x, y in zip(L, L[1:]))
|
||||
|
||||
|
||||
def non_increasing(L):
|
||||
return all(x >= y for x, y in zip(L, L[1:]))
|
||||
|
||||
|
||||
def monotonic(L):
|
||||
return non_decreasing(L) or non_increasing(L)
|
||||
|
||||
|
||||
def strictly_increasing(L):
|
||||
return all(x < y for x, y in zip(L, L[1:]))
|
||||
|
||||
|
||||
def strictly_decreasing(L):
|
||||
return all(x > y for x, y in zip(L, L[1:]))
|
||||
|
||||
|
||||
def strictly_monotonic(L):
|
||||
return strictly_increasing(L) or strictly_decreasing(L)
|
||||
|
||||
|
||||
def e_stop(
|
||||
early_stopping: list,
|
||||
train_acc: float,
|
||||
epoch: int,
|
||||
patience: int = 4,
|
||||
sensitivity: float = 1e-9,
|
||||
):
|
||||
early_stopping.append(train_acc)
|
||||
if epoch % 4 == 0 and epoch > 0:
|
||||
print("Value 1: {} > Value 2: {} > \
|
||||
Value 3: {}".format(early_stopping[0], \
|
||||
abs(early_stopping[1]-sensitivity), \
|
||||
abs(early_stopping[2]-sensitivity)))
|
||||
if train_acc > 0.5:
|
||||
if early_stopping[0] > abs(early_stopping[1]-sensitivity) and \
|
||||
early_stopping[1] > abs(early_stopping[2]-sensitivity):
|
||||
if patience in (0, 1):
|
||||
print("Stopping Early")
|
||||
return 1
|
||||
if epoch % patience == 0 and epoch > 0:
|
||||
early_stopping = early_stopping[-patience : len(early_stopping)]
|
||||
ini = early_stopping.pop(0)
|
||||
early_stopping = list(map(lambda x: x - sensitivity, early_stopping))
|
||||
early_stopping.insert(0, ini)
|
||||
values = ""
|
||||
for i, v in enumerate(early_stopping):
|
||||
values += f"Value {i+1}: {v} > "
|
||||
print(values)
|
||||
if (train_acc > 0.5) and not strictly_increasing(early_stopping):
|
||||
print("Stopping Early")
|
||||
return 1
|
||||
del early_stopping[:]
|
||||
return 0
|
||||
|
||||
|
||||
def energyBound(threshold: float=100000.0):
|
||||
def energy_bound(threshold: float = 100000.0):
|
||||
"""Stops training when a specified amount of energy is consumed"""
|
||||
try:
|
||||
energy = total_watt_consumed(cfg["pickle_path"])
|
||||
except Exception as e:
|
||||
|
|
@ -38,7 +76,7 @@ def energyBound(threshold: float=100000.0):
|
|||
return 0
|
||||
|
||||
|
||||
def accuracyBound(train_acc: float, threshold: float=0.99):
|
||||
def accuracy_bound(train_acc: float, threshold: float = 0.99):
|
||||
if train_acc >= threshold:
|
||||
print("Accuracy bound achieved")
|
||||
return 1
|
||||
|
|
|
|||
Loading…
Reference in New Issue