Ce serveur Gitlab sera éteint le 30 juin 2020, pensez à migrer vos projets vers les serveurs gitlab-research.centralesupelec.fr et gitlab-student.centralesupelec.fr !

Commit 21a4491f authored by Remi Hellequin's avatar Remi Hellequin

Initial commit of files

parents
*.swp
cifar10_init.o*
cifar10_init.e*
cifar10_run.o*
cifar10_run.e*
output
data
This diff is collapsed.
module load anaconda3/5.3
conda create --name cifar10
source activate cifar10
cd $PBS_O_WORKDIR
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/cuda-9.1/lib64 # maybe not necessary
export CUDA_HOME=/usr/local/cuda-9.1 # maybe not necessary
conda install pytorch torchvision -c pytorch
conda install matplotlib -c pytorch
conda env export > config/environment.yml # save conda environment description
name: cifar10
channels:
- pytorch
- defaults
dependencies:
- blas=1.0=mkl
- ca-certificates=2018.03.07=0
- certifi=2018.11.29=py37_0
- cffi=1.11.5=py37he75722e_1
- cycler=0.10.0=py37_0
- dbus=1.13.2=h714fa37_1
- expat=2.2.6=he6710b0_0
- fontconfig=2.13.0=h9420a91_0
- freetype=2.9.1=h8a8886c_1
- glib=2.56.2=hd408876_0
- gst-plugins-base=1.14.0=hbbd80ab_1
- gstreamer=1.14.0=hb453b48_1
- icu=58.2=h9c2bf20_1
- intel-openmp=2019.1=144
- jpeg=9b=h024ee3a_2
- kiwisolver=1.0.1=py37hf484d3e_0
- libedit=3.1.20170329=h6b74fdf_2
- libffi=3.2.1=hd88cf55_4
- libgcc-ng=8.2.0=hdf63c60_1
- libgfortran-ng=7.3.0=hdf63c60_0
- libpng=1.6.35=hbc83047_0
- libstdcxx-ng=8.2.0=hdf63c60_1
- libtiff=4.0.9=he85c1e1_2
- libuuid=1.0.3=h1bed415_2
- libxcb=1.13=h1bed415_1
- libxml2=2.9.8=h26e45fe_1
- matplotlib=3.0.2=py37h5429711_0
- mkl=2019.1=144
- mkl_fft=1.0.6=py37hd81dba3_0
- mkl_random=1.0.2=py37hd81dba3_0
- ncurses=6.1=he6710b0_1
- ninja=1.8.2=py37h6bb024c_1
- numpy=1.15.4=py37h7e9f1db_0
- numpy-base=1.15.4=py37hde5b4d6_0
- olefile=0.46=py37_0
- openssl=1.1.1a=h7b6447c_0
- pcre=8.42=h439df22_0
- pillow=5.3.0=py37h34e0f95_0
- pip=18.1=py37_0
- pycparser=2.19=py37_0
- pyparsing=2.3.0=py37_0
- pyqt=5.9.2=py37h05f1152_2
- python=3.7.1=h0371630_7
- python-dateutil=2.7.5=py37_0
- pytz=2018.7=py37_0
- qt=5.9.7=h5867ecd_1
- readline=7.0=h7b6447c_5
- setuptools=40.6.3=py37_0
- sip=4.19.8=py37hf484d3e_0
- six=1.12.0=py37_0
- sqlite=3.26.0=h7b6447c_0
- tk=8.6.8=hbc83047_0
- tornado=5.1.1=py37h7b6447c_0
- wheel=0.32.3=py37_0
- xz=5.2.4=h14c3975_4
- zlib=1.2.11=h7b6447c_3
- pytorch=1.0.0=py3.7_cuda9.0.176_cudnn7.4.1_1
- torchvision=0.2.1=py_2
- pip:
- torch==1.0.0
prefix: /home/hellequir/.conda/envs/cifar10
qsub -I -N gpu_test -l walltime=01:00:00 -l select=1:ncpus=24 -P admin -q gpuq
#!/bin/bash
#PBS -S /bin/bash
#PBS -N cifar10_init
#PBS -j oe
#PBS -l walltime=00:30:00
#PBS -l select=1:ncpus=1
#PBS -q gpuq
#PBS -P l2w
# Go to the directory where the job has been submitted
cd $PBS_O_WORKDIR
# Setup conda env - ensure your .conda dir is located on your workir, and move it if not
[ -L ~/.conda ] && unlink ~/.conda
[ -d ~/.conda ] && mv -v ~/.conda $WORKDIR
[ ! -d $WORKDIR/.conda ] && mkdir $WORKDIR/.conda
ln -s $WORKDIR/.conda ~/.conda
# Module load
module load anaconda3/5.3
# Environment config
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/cuda-9.1/lib64
export CUDA_HOME=/usr/local/cuda-9.1
# Create conda environment
conda env create -f config/environment.yml --force
# Save environment description
#source activate cifar10
#conda env export > config/environment.yml
#!/bin/bash
#PBS -S /bin/bash
#PBS -N cifar10_run
#PBS -j oe
#PBS -l walltime=01:00:00
#PBS -l select=1:ncpus=24
#PBS -q gpuq
#PBS -P test
# Go to the directory where the job has been submitted
cd $PBS_O_WORKDIR
# Module load
module load anaconda3/5.3
# Environment config
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/cuda-9.1/lib64
export CUDA_HOME=/usr/local/cuda-9.1
# Activate anaconda environment code
source activate cifar10
# Train the network
python scripts/train_network.py
#!/bin/bash
#PBS -S /bin/bash
#PBS -N cifar10_run
#PBS -j oe
#PBS -l walltime=01:00:00
#PBS -l select=1:ncpus=24
#PBS -q gpuq
#PBS -P test
# Go to the directory where the job has been submitted
cd $PBS_O_WORKDIR
# Module load
module load anaconda3/5.3
# Environment config
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/extras/CUPTI/lib64:/usr/local/cuda-9.1/lib64
export CUDA_HOME=/usr/local/cuda-9.1
# Activate anaconda environment code
source activate cifar10
# Train the network
python scripts/train_network_gpu.py
# -*- coding: utf-8 -*-
########################################################################
# 1. Loading and normalizing CIFAR10
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# Using ``torchvision``, it’s extremely easy to load CIFAR10.
import torch
import torchvision
import torchvision.transforms as transforms
import sys # MODIF - we need sys module to flush output in parallel
########################################################################
# The output of torchvision datasets are PILImage images of range [0, 1].
# We transform them to Tensors of normalized range [-1, 1].
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
########################################################################
# Let us show some of the training images, for fun.
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# print labels - MODIF : before showing images
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
# show images
imshow(torchvision.utils.make_grid(images))
# -*- coding: utf-8 -*-
########################################################################
# 1. Loading and normalizing CIFAR10
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Using ``torchvision``, it’s extremely easy to load CIFAR10.
import torch
import torchvision
import torchvision.transforms as transforms
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
########################################################################
# 2. Define a Convolutional Neural Network
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Copy the neural network from the Neural Networks section before and modify it to
# take 3-channel images (instead of 1-channel images as it was defined).
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
# MODIF - save network state into file
net.load_state_dict(torch.load('output/network.save'))
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.draw() # MODIF - replace plt.show(), same but continue the execution
########################################################################
# 5. Test the network on the test data
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# We have trained the network for 2 passes over the training dataset.
# But we need to check if the network has learnt anything at all.
#
# We will check this by predicting the class label that the neural network
# outputs, and checking it against the ground-truth. If the prediction is
# correct, we add the sample to the list of correct predictions.
#
# Okay, first step. Let us display an image from the test set to get familiar.
dataiter = iter(testloader)
images, labels = dataiter.next()
# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
########################################################################
# Okay, now let us see what the neural network thinks these examples above are:
outputs = net(images)
########################################################################
# The outputs are energies for the 10 classes.
# Higher the energy for a class, the more the network
# thinks that the image is of the particular class.
# So, let's get the index of the highest energy:
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))
plt.show() # MODIF - to ensure program won't shut
# -*- coding: utf-8 -*-
########################################################################
# 1. Loading and normalizing CIFAR10
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Using ``torchvision``, it’s extremely easy to load CIFAR10.
import torch
import torchvision
import torchvision.transforms as transforms
import sys # MODIF - we need sys module to flush output in parallel
########################################################################
# The output of torchvision datasets are PILImage images of range [0, 1].
# We transform them to Tensors of normalized range [-1, 1].
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
########################################################################
# 2. Define a Convolutional Neural Network
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Copy the neural network from the Neural Networks section before and modify it to
# take 3-channel images (instead of 1-channel images as it was defined).
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
########################################################################
# 3. Define a Loss function and optimizer
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Let's use a Classification Cross-Entropy loss and SGD with momentum.
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
########################################################################
# 4. Train the network
# ^^^^^^^^^^^^^^^^^^^^
#
# This is when things start to get interesting.
# We simply have to loop over our data iterator, and feed the inputs to the
# network and optimize.
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
sys.stdout.flush() # MODIF - stdout is flush every time you write in a multiprocessing subprocess
running_loss = 0.0
print('Finished Training')
# MODIF - save network state into file
torch.save(net.state_dict(), 'output/network.save')
########################################################################
# 5. Test the network on the test data
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# We have trained the network for 2 passes over the training dataset.
# But we need to check if the network has learnt anything at all.
#
# We will check this by predicting the class label that the neural network
# outputs, and checking it against the ground-truth. If the prediction is
# correct, we add the sample to the list of correct predictions.
#
# Let us look at how the network performs on the whole dataset.
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
########################################################################
# That looks waaay better than chance, which is 10% accuracy (randomly picking
# a class out of 10 classes).
# Seems like the network learnt something.
#
# Hmmm, what are the classes that performed well, and the classes that did
# not perform well:
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(4):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(10):
print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))
# -*- coding: utf-8 -*-
########################################################################
# 1. Loading and normalizing CIFAR10
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Using ``torchvision``, it’s extremely easy to load CIFAR10.
import torch
import torchvision
import torchvision.transforms as transforms
import sys # MODIF - we need sys module to flush output in parallel
########################################################################
# The output of torchvision datasets are PILImage images of range [0, 1].
# We transform them to Tensors of normalized range [-1, 1].
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
########################################################################
# 2. Define a Convolutional Neural Network
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Copy the neural network from the Neural Networks section before and modify it to
# take 3-channel images (instead of 1-channel images as it was defined).
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
########################################################################
# 3. Define a Loss function and optimizer
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# Let's use a Classification Cross-Entropy loss and SGD with momentum.
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
# MODIF - use cuda device
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
########################################################################
# 4. Train the network
# ^^^^^^^^^^^^^^^^^^^^
#
# This is when things start to get interesting.
# We simply have to loop over our data iterator, and feed the inputs to the
# network and optimize.
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
#net = nn.DataParallel(net) # MODIF - test for multi GPU. Not working atm
net.to(device)
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
sys.stdout.flush() # MODIF - stdout is flush every time you write in a multiprocessing subprocess
running_loss = 0.0
print('Finished Training')
# MODIF - save network state into file
torch.save(net.state_dict(), 'output/network.save')
########################################################################
# 5. Test the network on the test data
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# We have trained the network for 2 passes over the training dataset.
# But we need to check if the network has learnt anything at all.
#
# We will check this by predicting the class label that the neural network
# outputs, and checking it against the ground-truth. If the prediction is
# correct, we add the sample to the list of correct predictions.
#
# Let us look at how the network performs on the whole dataset.
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
########################################################################
# That looks waaay better than chance, which is 10% accuracy (randomly picking
# a class out of 10 classes).
# Seems like the network learnt something.
#
# Hmmm, what are the classes that performed well, and the classes that did
# not perform well:
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(4):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(10):
print('Accuracy of %5s : %2d %%' % (classes[i], 100 * class_correct[i] / class_total[i]))
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment