Did some Python formatting

This commit is contained in:
Eddie Cueto 2023-06-30 11:09:54 +01:00
parent 0f8ee842a3
commit 3c928cc350
6 changed files with 150 additions and 143 deletions

View File

@ -9,32 +9,15 @@ with (open("configuration.pkl", "rb")) as file:
except EOFError:
break
#with open("frq", "r") as file:
# frq = int(file.read())
#with open("bay", "r") as file:
# bay = int(file.read())
# pickle_name = "{}_wattdata_{}.pkl".format(model_t,size)
# print("GPU energy file config: {}".format(pickle_name))
#if frq == 1:
# model_t = "freq"
# with open("tmp", "r") as file:
# size = float(file.read())
#if bay == 1:
# model_t = "bayes"
# with open("tmp", "r") as file:
# size = int(file.read())
#pickle_name = "{}_wattdata_{}.pkl".format(model_t,size)
#print("GPU energy file config: {}".format(pickle_name))
#print(cfg)
# print(cfg)
if __name__ == '__main__':
dataDump = []
#var = True
#pickling_on = open("wattdata.pickle","wb")
while True:
try:
dataDump.append(get_sample_of_gpu())
@ -42,17 +25,5 @@ if __name__ == '__main__':
pickle.dump(dataDump, f)
except EOFError:
warn('Pickle ran out of space')
size += 0.01
finally:
f.close()
#if retcode == 0:
#break
#pickle.dump(dataDump, pickling_on)
#pickling_on.close()

View File

@ -7,16 +7,21 @@ 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")
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")
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]')
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())

0
gpu_power_func.py Normal file → Executable file
View File

View File

@ -10,7 +10,6 @@ import numpy as np
from datetime import datetime
from torch.nn import functional as F
from torch.optim import Adam, lr_scheduler
from gpu_power_func import total_watt_consumed
from models.BayesianModels.BayesianLeNet import BBBLeNet
from models.BayesianModels.BayesianAlexNet import BBBAlexNet
from models.BayesianModels.Bayesian3Conv3FC import BBB3Conv3FC
@ -27,18 +26,23 @@ with (open("configuration.pkl", "rb")) as file:
# CUDA settings
device = torch.device("cuda:1" 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"])
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)
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 = []
@ -48,7 +52,8 @@ def train_model(net, optimizer, criterion, trainloader, num_ens=1, beta_type=0.1
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):
@ -60,7 +65,8 @@ def train_model(net, optimizer, criterion, trainloader, num_ens=1, beta_type=0.1
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()
@ -70,7 +76,8 @@ def train_model(net, optimizer, criterion, trainloader, num_ens=1, beta_type=0.1
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
@ -78,7 +85,8 @@ def validate_model(net, criterion, validloader, num_ens=1, beta_type=0.1, epoch=
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)
@ -87,7 +95,8 @@ def validate_model(net, criterion, validloader, num_ens=1, beta_type=0.1, epoch=
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))
@ -113,10 +122,12 @@ 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)
net = getModel(net_type, inputs, outputs, priors, layer_type,
activation_type).to(device)
ckpt_dir = f'checkpoints/{dataset}/bayesian'
ckpt_name = f'checkpoints/{dataset}/bayesian/model_{net_type}_{layer_type}_{activation_type}_{cfg["model"]["size"]}.pt'
ckpt_name = f'checkpoints/{dataset}/bayesian/model_{net_type}_{layer_type}\
_{activation_type}_{cfg["model"]["size"]}.pt'
if not os.path.exists(ckpt_dir):
os.makedirs(ckpt_dir, exist_ok=True)
@ -126,25 +137,40 @@ 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)
#valid_loss_max = np.Inf
#if stp == 2:
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, 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_ens=valid_ens, beta_type=beta_type, epoch=epoch, num_epochs=n_epochs)
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_ens=valid_ens,
beta_type=beta_type,
epoch=epoch,
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: {:.4f} \tValidation Loss: {:.4f} \tValidation Accuracy: {:.4f} \ttrain_kl_div: {:.4f}'.format(
epoch, train_loss, train_acc, valid_loss, valid_acc, train_kl))
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))
if stp == 2:
print('Using early stopping')
if earlyStopping(early_stop,valid_acc,epoch,cfg["model"]["sens"]) == 1:
if earlyStopping(early_stop, valid_acc, epoch,
cfg["model"]["sens"]) == 1:
break
elif stp == 3:
print('Using energy bound')
@ -152,7 +178,7 @@ def run(dataset, net_type):
break
elif stp == 4:
print('Using accuracy bound')
if accuracyBound(train_acc,cfg.acc_thrs) == 1:
if accuracyBound(train_acc, cfg.acc_thrs) == 1:
break
else:
print('Training for {} epochs'.format(cfg["model"]["n_epochs"]))
@ -162,10 +188,10 @@ def run(dataset, net_type):
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:
pickle.dump(train_data, f)
if __name__ == '__main__':
now = datetime.now()
current_time = now.strftime("%H:%M:%S")
@ -174,4 +200,3 @@ if __name__ == '__main__':
now = datetime.now()
current_time = now.strftime("%H:%M:%S")
print("Final Time =", current_time)

View File

@ -2,15 +2,12 @@ from __future__ import print_function
import os
import data
import torch
#import utils
import pickle
import metrics
import argparse
import numpy as np
import torch.nn as nn
from datetime import datetime
from torch.optim import Adam, lr_scheduler
from gpu_power_func import total_watt_consumed
from models.NonBayesianModels.LeNet import LeNet
from models.NonBayesianModels.AlexNet import AlexNet
from stopping_crit import earlyStopping, energyBound, accuracyBound
@ -27,23 +24,24 @@ with (open("configuration.pkl", "rb")) as file:
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")
def getModel(net_type, inputs, outputs,wide=cfg["model"]["size"]):
def getModel(net_type, inputs, outputs, wide=cfg["model"]["size"]):
if (net_type == 'lenet'):
return LeNet(outputs, inputs,wide)
return LeNet(outputs, inputs, wide)
elif (net_type == 'alexnet'):
return AlexNet(outputs, inputs)
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):
train_loss = 0.0
net.train()
accs = []
for data, target in train_loader:
data, target = data.to(device), target.to(device)
for datas, target in train_loader:
data, target = datas.to(device), target.to(device)
optimizer.zero_grad()
output = net(data)
loss = criterion(output, target)
@ -58,8 +56,8 @@ def validate_model(net, criterion, valid_loader):
valid_loss = 0.0
net.eval()
accs = []
for data, target in valid_loader:
data, target = data.to(device), target.to(device)
for datas, target in valid_loader:
data, target = datas.to(device), target.to(device)
output = net(data)
loss = criterion(output, target)
valid_loss += loss.item()*data.size(0)
@ -82,7 +80,8 @@ def run(dataset, net_type):
net = getModel(net_type, inputs, outputs).to(device)
ckpt_dir = f'checkpoints/{dataset}/frequentist'
ckpt_name = f'checkpoints/{dataset}/frequentist/model_{net_type}_{cfg["model"]["size"]}.pt'
ckpt_name = f'checkpoints/{dataset}/frequentist/model\
_{net_type}_{cfg["model"]["size"]}.pt'
if not os.path.exists(ckpt_dir):
os.makedirs(ckpt_dir, exist_ok=True)
@ -92,35 +91,41 @@ def run(dataset, net_type):
criterion = nn.CrossEntropyLoss()
optimizer = Adam(net.parameters(), lr=lr)
lr_sched = lr_scheduler.ReduceLROnPlateau(optimizer, patience=6, verbose=True)
#valid_loss_min = np.Inf
#if stp == 2:
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):
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_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))
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))
if stp == 2:
#print('Using early stopping')
if earlyStopping(early_stop,valid_acc,epoch,cfg["model"]["sens"]) == 1:
# print('Using early stopping')
if earlyStopping(early_stop, valid_acc, epoch,
cfg["model"]["sens"]) == 1:
break
elif stp == 3:
#print('Using energy bound')
# print('Using energy bound')
if energyBound(cfg["model"]["energy_thrs"]) == 1:
break
elif stp == 4:
#print('Using accuracy bound')
if accuracyBound(train_acc,cfg["model"]["acc_thrs"]) == 1:
# print('Using accuracy bound')
if accuracyBound(train_acc,
cfg["model"]["acc_thrs"]) == 1:
break
else:
print('Training for {} epochs'.format(cfg["model"]["n_epochs"]))
@ -142,4 +147,3 @@ if __name__ == '__main__':
now = datetime.now()
current_time = now.strftime("%H:%M:%S")
print("Final Time =", current_time)

View File

@ -12,15 +12,16 @@ def kill(proc_pid):
proc.kill()
process.kill()
cfg = {
"model": {"net_type": None, "type": None, "size": None, "layer_type": "lrt",
"activation_type": "softplus", "priors": {
"model": {"net_type": None, "type": None, "size": None, "layer_type":
"lrt", "activation_type": "softplus", "priors": {
'prior_mu': 0,
'prior_sigma': 0.1,
'posterior_mu_initial': (0, 0.1), # (mean, std) normal_
'posterior_rho_initial': (-5, 0.1), # (mean, std) normal_
'posterior_mu_initial': (0, 0.1), # (mean,std) normal_
'posterior_rho_initial': (-5, 0.1), # (mean,std) normal_
},
"n_epochs": 3,
"n_epochs": 100,
"sens": 1e-9,
"energy_thrs": 10000,
"acc_thrs": 0.99,
@ -30,7 +31,8 @@ cfg = {
"batch_size": 256,
"train_ens": 1,
"valid_ens": 1,
"beta_type": 0.1, # 'Blundell', 'Standard', etc. Use float for const value
"beta_type": 0.1, # 'Blundell','Standard',etc.
# Use float for const value
},
"data": None,
"stopping_crit": None,
@ -46,10 +48,10 @@ if all(v is None for v in check):
elif None in check:
if args['f'] is not None:
cmd = ["python", "main_frequentist.py"]
cfg["model"]["type"] = "frequentist"
cfg["model"]["type"] = "freq"
elif args['b'] is not None:
cmd = ["python", "main_bayesian.py"]
cfg["model"]["type"] = "bayesian"
cfg["model"]["type"] = "bayes"
else:
raise Exception("Only one argument allowed")
@ -76,13 +78,14 @@ else:
cfg["save"] = 0
cfg["pickle_path"] = "{}_wattdata_{}.pkl".format(cfg["model"]["type"],cfg["model"]["size"])
cfg["pickle_path"] = "{}_wattdata_{}.pkl".format(cfg["model"]["type"],
cfg["model"]["size"])
with open("configuration.pkl", "wb") as f:
pickle.dump(cfg, f)
#print(args)
#print(cfg)
# print(args)
# print(cfg)
sleep(3)
@ -104,12 +107,12 @@ path = path.replace('\n', '')
startWattCounter = 'python ' + path + '/amd_sample_draw.py'
p1 = sub.Popen(cmd)
p2 = sub.Popen(startWattCounter.split(),stdin=sub.PIPE,stdout=sub.PIPE, stderr=sub.PIPE)
p3 = sub.Popen(cmd2,stdin=sub.PIPE,stdout=sub.PIPE, stderr=sub.PIPE)
p4 = sub.Popen(cmd3,stdin=sub.PIPE,stdout=sub.PIPE, stderr=sub.PIPE)
p5 = sub.Popen(cmd4,stdin=sub.PIPE,stdout=sub.PIPE, stderr=sub.PIPE)
p2 = sub.Popen(startWattCounter.split(), stdin=sub.PIPE, stdout=sub.PIPE,
stderr=sub.PIPE)
p3 = sub.Popen(cmd2, stdin=sub.PIPE, stdout=sub.PIPE, stderr=sub.PIPE)
p4 = sub.Popen(cmd3, stdin=sub.PIPE, stdout=sub.PIPE, stderr=sub.PIPE)
p5 = sub.Popen(cmd4, stdin=sub.PIPE, stdout=sub.PIPE, stderr=sub.PIPE)
retcode = p1.wait()
print("Return code: {}".format(retcode))
@ -119,4 +122,3 @@ kill(p2.pid)
kill(p3.pid)
kill(p4.pid)
kill(p5.pid)