Running Alexnet on VOC2012 using pytorch for object detection

Updated: Sep 12, 2020

After scouring the internet for a couple of days looking for a code to run alexnet on VOC12 data for classification ending in vain, I had to write the integrated code myself and I a sharing the same for anyone to reuse.

Due to lack of time I am posting the codes for sorting & training separately. I will make an update when I get time, to write a single unified code. Meanwhile if anyone faces any error, just drop a comment (or email to with details (including pytorh and torchvision versions) and I will look into it

I had a choice to write a custom dataloader or convert the data into a pre-defined data loader structure. I chose the latter and the code basically converts the VOC12 data into Imgefolder data structure. Just change the root directory string in the and run it.

This would create the following folders with hierarchvaliy:

|classes |train (training set) |<folders with class names> |val (validation set) |<folders with classnames>

After this go to . It contains the actual code to initialize your neeural network and configure your net (whether you want to download pre trained model, what is your input, how many output classes you have, )

Download Link for Code files

Image Sorting Code(

Training and Model Saving Code (



## Place this code in the same folder where Imagefolder exists

# creating data folder

import shutil

from shutil import copyfile

import os

all_files = os.listdir("Main/")

# print(all_files[0])


all_files_set = set(all_files)

# print(all_files_set)


# To create all class directories

for name in all_files_set:

#print (name)

temp = name.split('_')



# if((os.path.isdir("classes/"+temp[0]))):

print("Directory already exists \n \n \n")



# os.makedirs("classes/"+temp[0])

if(temp[0] == "train.txt" or temp[0] == "val.txt" or temp[0] =="trainval.txt"):


for name in all_files_set:

temp_f = name.split('_')

if (temp_f[0] == "train.txt" or temp_f[0] == "val.txt" or temp_f[0] =="trainval.txt"):

print("\n ************** \n skipped train, val & trainval text files \n ************** \n ")


if(temp_f[1] == "val.txt"):

# if(temp_f[1] == "train.txt"):

print("Opening Text file: "+name)

# print(name)

f = open("Main/"+name, "r")

lines = list(f)

# print(lines)

# lines = f.readlines()


for line in lines:

temp = line.split(" ")

# print(temp[1])

print (temp)

if (temp[1] == '-1\n'):


elif (temp[2] == '1\n'):

# copyfile(src, dst)


shutil.copy("../JPEGImages/"+temp[0]+".jpg", "classes_val/"+temp_f[0]+"/")

# shutil.copy("../JPEGImages/"+temp[0]+".jpg", "classes/"+temp_f[0]+"/")



from __future__ import print_function

from __future__ import division

import torch

import torch.nn as nn

import torch.optim as optim

import numpy as np

import torchvision

from torchvision import datasets, models, transforms

import matplotlib.pyplot as plt

import time

import os

import copy

# import voc

def run():

print("PyTorch Version: ",torch.__version__)

print("Torchvision Version: ",torchvision.__version__)

# Top level data directory. Here we assume the format of the directory conforms

# to the ImageFolder structure

data_dir = "./classes/"

# Models to choose from [resnet, alexnet, vgg, squeezenet, densenet, inception]

model_name = "alexnet"

# Number of classes in the dataset

num_classes = 20

# Batch size for training (change depending on how much memory you have)

batch_size = 8

# Number of epochs to train for

num_epochs = 1

# Flag for feature extracting. When False, we finetune the whole model,

# when True we only update the reshaped layer params

feature_extract = True

def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False):

since = time.time()

val_acc_history = []

best_model_wts = copy.deepcopy(model.state_dict())

best_acc = 0.0

for epoch in range(num_epochs):

print('Epoch {}/{}'.format(epoch, num_epochs - 1))

print('-' * 10)

# Each epoch has a training and validation phase

for phase in ['train', 'val']:

if phase == 'train':

model.train() # Set model to training mode


model.eval() # Set model to evaluate mode

running_loss = 0.0

running_corrects = 0

# Iterate over data.

for inputs, labels in dataloaders[phase]:

inputs =

labels =

# zero the parameter gradients


# forward

# track history if only in train

with torch.set_grad_enabled(phase == 'train'):

# Get model outputs and calculate loss

# Special case for inception because in training it has an auxiliary output. In train

# mode we calculate the loss by summing the final output and the auxiliary output

# but in testing we only consider the final output.

if is_inception and phase == 'train':

# From

outputs, aux_outputs = model(inputs)

loss1 = criterion(outputs, labels)

loss2 = criterion(aux_outputs, labels)

loss = loss1 + 0.4*loss2


outputs = model(inputs)

loss = criterion(outputs, labels)

_, preds = torch.max(outputs, 1)

# backward + optimize only if in training phase

if phase == 'train':



# statistics

running_loss += loss.item() * inputs.size(0)

running_corrects += torch.sum(preds ==

epoch_loss = running_loss / len(dataloaders[phase].dataset)

epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)

print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))

# deep copy the model

if phase == 'val' and epoch_acc > best_acc:

best_acc = epoch_acc

best_model_wts = copy.deepcopy(model.state_dict())

if phase == 'val':



time_elapsed = time.time() - since

print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))

print('Best val Acc: {:4f}'.format(best_acc))

# load best model weights

model.load_state_dict(best_model_wts), "./classes/abc.pth")

return model, val_acc_history


#saving a model weights, ./classes)


def set_parameter_requires_grad(model, feature_extracting):

if feature_extracting:

for param in model.parameters():

param.requires_grad = False

# model.classifier[6] = nn.Linear(4096,num_classes)

def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):

# Initialize these variables which will be set in this if statement. Each of these

# variables is model specific.

model_ft = None

input_size = 0

if model_name == "resnet":

""" Resnet18


model_ft = models.resnet18(pretrained=use_pretrained)

set_parameter_requires_grad(model_ft, feature_extract)

num_ftrs = model_ft.fc.in_features

model_ft.fc = nn.Linear(num_ftrs, num_classes)

input_size = 224

elif model_name == "alexnet":

""" Alexnet


model_ft = models.alexnet(pretrained=use_pretrained)

set_parameter_requires_grad(model_ft, feature_extract)

num_ftrs = model_ft.classifier[6].in_features

model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)

input_size = 224

elif model_name == "vgg":

""" VGG11_bn


model_ft = models.vgg11_bn(pretrained=use_pretrained)

set_parameter_requires_grad(model_ft, feature_extract)

num_ftrs = model_ft.classifier[6].in_features

model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)

input_size = 224

elif model_name == "squeezenet":

""" Squeezenet


model_ft = models.squeezenet1_0(pretrained=use_pretrained)

set_parameter_requires_grad(model_ft, feature_extract)

model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))

model_ft.num_classes = num_classes

input_size = 224

elif model_name == "densenet":

""" Densenet


model_ft = models.densenet121(pretrained=use_pretrained)

set_parameter_requires_grad(model_ft, feature_extract)

num_ftrs = model_ft.classifier.in_features

model_ft.classifier = nn.Linear(num_ftrs, num_classes)

input_size = 224

elif model_name == "inception":

""" Inception v3

Be careful, expects (299,299) sized images and has auxiliary output


model_ft = models.inception_v3(pretrained=use_pretrained)

set_parameter_requires_grad(model_ft, feature_extract)

# Handle the auxilary net

num_ftrs = model_ft.AuxLogits.fc.in_features

model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)

# Handle the primary net

num_ftrs = model_ft.fc.in_features

model_ft.fc = nn.Linear(num_ftrs,num_classes)

input_size = 299


print("Invalid model name, exiting...")


return model_ft, input_size

# Initialize the model for this run

model_ft, input_size = initialize_model(model_name, num_classes, feature_extract, use_pretrained=True)

# Print the model we just instantiated


# Data augmentation and normalization for training

# Just normalization for validation

data_transforms = {

'train': transforms.Compose([




transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])


'val': transforms.Compose([




transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])



print("Initializing Datasets and Dataloaders...")

# Create training and validation datasets

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}

# Create training and validation dataloaders

dataloaders_dict = {x:[x], batch_size=batch_size, shuffle=True, num_workers=4) for x in ['train', 'val']}

# Create training and validation datasets

#image_datasets = voc.VOCDetection(data_dir, year='2012', image_set='train', download=False, transform=transform, target_transform=None)

# Create training and validation dataloaders

#dataloaders_dict =, batch_size=4, shuffle=True, num_workers=2)

# Detect if we have a GPU available

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# device = "cpu"

# Send the model to GPU

model_ft =

# Gather the parameters to be optimized/updated in this run. If we are

# finetuning we will be updating all parameters. However, if we are

# doing feature extract method, we will only update the parameters

# that we have just initialized, i.e. the parameters with requires_grad

# is True.

params_to_update = model_ft.parameters()

print("Params to learn:")

if feature_extract:

params_to_update = []

for name,param in model_ft.named_parameters():

if param.requires_grad == True:




for name,param in model_ft.named_parameters():

if param.requires_grad == True:


# Observe that all parameters are being optimized #lr=0.0001

optimizer_ft = optim.SGD(params_to_update, lr=0.9, momentum=0.9)

# Setup the loss fxn

criterion = nn.CrossEntropyLoss()

# Train and evaluate

model_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))

print("Chekcpoint save started")

#, "model_{}.pt".format(epoch))

#, '')

print("Chekcpoint saved")

if __name__ == '__main__':


#torchvision #pytorch #AI #computervision

471 views0 comments

Recent Posts

See All

I have been a loyal digikey customer for past 7 years and there's nothing to complaint given the vast catalog including everything one can think of or not. Being in Mumbai, a quick alternative is some