aditya239233 / pedestrian-segmentation

Image Segmentation on Pedestrians

Hi there 👋

My name is Aditya Chandrasekhar and I'm a Software Engineer at United Overseas Bank, Singapore. I love software automation and looking for cool ideas to bring to life

📝 Blog posts

• Analysis of the Software Architecture of Netflix
• Predicting Energy Consumption using Neural Networks and historical temperature data

Connect with me

   

pedestrian-segmentation's Issues

why cant i use this code for predicting images other than dataset images

In predictsegmentation.py
when i upload the image from the Penn-Fudan Dataset ,I am getting segmentation correctly like below

when i run the code for an image which i have dowloaded from the net, the segmentation is not happening ,it is showing the blank image like below

The code is only working for the images in the Penn-Fudan Dataset, but when i run the code on images other than the Penn-Fudan Dataset it is not working.
What is the main reason for it?

ForkingPickler(file, protocol).dump(obj) BrokenPipeError: [Errno 32] Broken pipe

from dataset import Dataset
from model import model
from helper import add_pallet, collate_fn, get_transform

import torch
from PIL import Image
from matplotlib import pyplot as plt
from engine import train_one_epoch, evaluate

#%%
image = Image.open('../data/PNGImages/PennPed00035.png')
mask = Image.open('../data/PedMasks/PennPed00035_mask.png')
_, axs = plt.subplots(1, 2, figsize=(12, 12))
axs = axs.flatten()
imgs = [image, mask]
for img, ax in zip(imgs, axs):
ax.imshow(img)
plt.show()

#%%
dataset_train = Dataset('../data/', get_transform(train=True))
dataset_test = Dataset('../data/', get_transform(train=False))

print(dataset_train[0])

#%%
torch.manual_seed(1)
indices = torch.randperm(len(dataset_train)).tolist()
dataset_train = torch.utils.data.Subset(dataset_train, indices[:-50])
dataset_test = torch.utils.data.Subset(dataset_test, indices[-50:])

define training and validation data loaders

data_loader_train = torch.utils.data.DataLoader(
dataset_train, batch_size=2, shuffle=True, num_workers=4,
collate_fn=collate_fn)

data_loader_test = torch.utils.data.DataLoader(
dataset_test, batch_size=1, shuffle=False, num_workers=4,
collate_fn=collate_fn)

#%%
device = torch.device('cpu')

our dataset has two classes only - background and person

num_classes = 2

model = model(num_classes)

model.to(device)

params = [p for p in model.parameters() if p.requires_grad]
optimizer = torch.optim.SGD(params, lr=0.005,
momentum=0.9, weight_decay=0.0005)
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,
gamma=0.1)

#%%
num_epochs = 10

for epoch in range(num_epochs):
train_one_epoch(model, optimizer, data_loader_train, device, epoch, print_freq=10)
lr_scheduler.step()

evaluate(model, data_loader_test, device=device)

torch.save(model.state_dict(), "../model/model.pth")

#%%
img, _ = dataset_test[0]

model.eval()
with torch.no_grad():
prediction = model([img.to(device)])
print(prediction)
#%%
image = Image.fromarray(img.mul(255).permute(1, 2, 0).byte().numpy())
mask = Image.fromarray(prediction[0]['masks'][0, 0].mul(255).byte().cpu().numpy())
_, axs = plt.subplots(1, 2, figsize=(12, 12))
axs = axs.flatten()
imgs = [image, mask]
for img, ax in zip(imgs, axs):
ax.imshow(img)
plt.show()

When I run this code i am getting BrokenPipeError
Traceback (most recent call last):
File "", line 1, in
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 114, in _main
prepare(preparation_data)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 225, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
run_name="mp_main")
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\PedestrianDetection.py", line 63, in
train_one_epoch(model, optimizer, data_loader_train, device, epoch, print_freq=10)
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\engine.py", line 26, in train_one_epoch
for images, targets in metric_logger.log_every(data_loader, print_freq, header):
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\utils.py", line 201, in log_every
for obj in iterable:
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 355, in iter
return self._get_iterator()
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 301, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 914, in init
w.start()
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\popen_spawn_win32.py", line 46, in init
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 143, in get_preparation_data
_check_not_importing_main()
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py", line 136, in _check_not_importing_main
is not going to be frozen to produce an executable.''')
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

Traceback (most recent call last):
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\PedestrianDetection.py", line 63, in
train_one_epoch(model, optimizer, data_loader_train, device, epoch, print_freq=10)
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\engine.py", line 26, in train_one_epoch
for images, targets in metric_logger.log_every(data_loader, print_freq, header):
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\utils.py", line 201, in log_every
for obj in iterable:
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 355, in iter
return self._get_iterator()
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 301, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 914, in init
w.start()
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "C:\Users\Prem\AppData\Local\Programs\Python\Python37\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
BrokenPipeError: [Errno 32] Broken pipe

I didn't understand why i am getting this error
Can you please explain this? Thank u

from vision.references.detection import utils ModuleNotFoundError: No module named 'vision'

import torchvision
from vision.references.detection import utils
import vision.references.detection.transforms as T

def get_transform(train):
# data augmentation
transforms = []
transforms.append(T.ToTensor())

if train:
    transforms.append(T.RandomHorizontalFlip(0.5))

return T.Compose(transforms)

def add_pallet(mask):
mask.putpalette([
0, 0, 0, # black background
255, 0, 0, # index 1 is red
255, 255, 0, # index 2 is yellow
255, 153, 0, # index 3 is orange
])
return mask

def collate_fn(batch):
return tuple(zip(*batch))

error i am getting is
Traceback (most recent call last):
File "D:\MINI PROJECT\Pedestrian-Segmentation-main\src\helper.py", line 2, in
from vision.references.detection import utils
ModuleNotFoundError: No module named 'vision'

I cannot use this code for predicting images other than dataset images

Yes, For both the outputs, I am reading the file in the exact same way.
The code is working perfectly for all images in the Penn-Fudan Dataset .
when I run the code for an image which I have dowloaded from the net, the segmentation is not happening ,it is showing the blank image like below

The code is only working for the images in the Penn-Fudan Dataset, but when I run the code on images other than the Penn-Fudan Dataset it is not working.
What is the main reason for it?

why cant i use this code for predicting images other than dataset images

when i tested this code on other images , other than dataset images,it is not predicting
what is the main reason for this?