Differences

This shows you the differences between two versions of the page.

--- cs501r_f2018:lab4 [2018/09/24 21:46]
shreeya
+++ cs501r_f2018:lab4 [2021/06/30 23:42]
@@ Line 1: / Line 1: @@
-=====BYU CS 501R - Deep Learning:Theory and Practice - Lab 4=====
-====Objective:====
-  * To build a dense prediction model
-  * To begin reading current papers in DNN research
-----
-====Deliverable:====
-{{ :cs501r_f2016:pos_test_000072.png?direct&200|}}
-{{ :cs501r_f2016:pos_test_000072_output.png?direct&200|}}
-For this lab, you will turn in a notebook that describes your efforts at
-creating a pytorch radiologist.  Your final deliverable is a
-notebook that has (1) deep network, (2) cost
-function, (3) method of calculating accuracy, (4) an image that
-shows the dense prediction produced by your network on the
-''pos_test_000072.png'' image.  This is an image in the test set that
-your network will not have seen before.  This image, and the ground truth labeling, is shown at the right. (And is contained in the downloadable dataset below).
-----
-====Grading standards:====
-Your notebook will be graded on the following:
-  * 40% Proper design, creation and debugging of a dense prediction network
-  * 40% Proper implementation of a loss function and train/test set accuracy measure
-  * 10% Tidy visualizations of loss of your dense predictor during training
-  * 10% Test image output
-----
-====Data set:====
-{{ :cs501r_f2016:pos_train_000200.png?direct&200|}}
-{{ :cs501r_f2016:pos_train_000200_output.png?direct&200|}}
-The data is given as a set of 1024x1024 PNG images.  Each input image
-(in the ''inputs'' directory) is an RGB image of a section of tissue,
-and there a file with the same name (in the ''outputs'' directory) that
-has a dense labeling of whether or not a section of tissue is
-cancerous (white pixels mean "cancerous", while black pixels mean "not
-cancerous").
-The data has been pre-split for you into test and training splits.
-Filenames also reflect whether or not the image has any cancer at all
-(files starting with ''pos_'' have some cancerous pixels, while files
-starting with ''neg_'' have no cancer anywhere).  All of the data is
-hand-labeled, so the dataset is not very large.  That means that
-overfitting is a real possibility.
-[[http://liftothers.org/cancer_data.tar.gz|The data can be downloaded here.]] //Please note that this dataset is not publicly available, and should not be redistributed.//
-----
-====Description:====
-For this lab, you will implement a virtual radiologist.  You are given
-images of possibly cancerous tissue samples, and you must build a
-detector that identifies where in the tissue cancer may reside.
-**Part 1: Implement a dense predictor**
-In previous labs and lectures, we have talked about DNNs that classify an
-entire image as a single class.  Here, however, we are interested in a
-more nuanced classification: given an input image, we would like to
-identify each **pixel** that is possibly cancerous.  That means that
-instead of a single output, your network should output an "image", where
-each output pixel of your network represents the probability that a
-pixel is cancerous.
-**Part 1a: Implement your network topology**
-{{ :cs501r_f2016:screen_shot_2017-10-10_at_10.11.55_am.png?direct&200|}}
-Use the "Deep Convolution U-Net" from this paper: [[https://arxiv.org/pdf/1505.04597.pdf|U-Net: Convolutional Networks for Biomedical Image Segmentation]] (See figure 1, replicated at the right).  This should be fairly easy to implement given the
-''conv'' helper functions that you implemented previously; you
-may also need the pytorch function ''torch.cat'' and ''nn.ConvTranspose2d''
-''torch.cat'' allows you to concatenate tensors. ''nn.ConvTranspose2d'' is the opposite of ''nn.Conv2d''. It is used to bring an image from low res to higher res. [[https://towardsdatascience.com/up-sampling-with-transposed-convolution-9ae4f2df52d0|This blog]] should help you understand this function in detail.
-//Note that the simplest network you could implement (with all the desired properties) is just a single convolution layer with two filters and no relu!  Why is that?  (of course it wouldn't work very well!)//
-**Part 1b: Implement a cost function**
-You should still use cross-entropy as your cost function, but you may
-need to think hard about how exactly to set this up -- your network
-should output cancer/not-cancer probabilities for each pixel, which
-can be viewed as a two-class classification problem.
-**Part 2: Plot performance over time**
-Please generate a plot that shows loss on the training set as a function of training time.  Make sure your axes are labeled!
-**Part 3: Generate a prediction on the ''pos_test_000072.png'' image**
-Calculate the output of your trained network on the ''pos_test_000072.png'' image, then make a hard decision (cancerous/not-cancerous) for each pixel.  The resulting image should be black-and-white, where white pixels represent things you think are probably cancerous.
-----
-====Hints:====
-The focus of this lab is to learn how to make deep neural nets and implement loss function. Therefore we'll help you with the implementation of Dataset.
-<code python>
-class CancerDataset(Dataset):
-  def __init__(self, root, download=True, size=512, train=True):
-    if download and not os.path.exists(os.path.join(root, 'cancer_data')):
-      datasets.utils.download_url('http://liftothers.org/cancer_data.tar.gz', root, 'cancer_data.tar.gz', None)
-      self.extract_gzip(os.path.join(root, 'cancer_data.tar.gz'))
-      self.extract_tar(os.path.join(root, 'cancer_data.tar'))
-    postfix = 'train' if train else 'test'
-    root = os.path.join(root, 'cancer_data', 'cancer_data')
-    self.dataset_folder = torchvision.datasets.ImageFolder(os.path.join(root, 'inputs_' + postfix) ,transform = transforms.Compose([transforms.Resize(size),transforms.ToTensor()]))
-    self.label_folder = torchvision.datasets.ImageFolder(os.path.join(root, 'outputs_' + postfix) ,transform = transforms.Compose([transforms.Resize(size),transforms.ToTensor()]))
-  @staticmethod
-  def extract_gzip(gzip_path, remove_finished=False):
-    print('Extracting {}'.format(gzip_path))
-    with open(gzip_path.replace('.gz', ''), 'wb') as out_f, gzip.GzipFile(gzip_path) as zip_f:
-      out_f.write(zip_f.read())
-    if remove_finished:
-      os.unlink(gzip_path)
-  @staticmethod
-  def extract_tar(tar_path):
-    print('Untarring {}'.format(tar_path))
-    z = tarfile.TarFile(tar_path)
-    z.extractall(tar_path.replace('.tar', ''))
-  def __getitem__(self,index):
-    img = self.dataset_folder[index]
-    label = self.label_folder[index]
-    return img[0] * 255,label[0][0]
-  def __len__(self):
-    return len(self.dataset_folder)
-</code>
-The tricky part here is that Imagefolder takes a folder of images. When you have both inputs and outputs folder inside cancer_data, it does not know that outputs is label. To get over this problem, I created a layer of folders that looks like this: cancer_data -> train_input -> train_input->all image files and similar for all other folders.(we are looking at other options of making the dataset...)
-You are welcome to resize your input images, although don't make them
-so small that the essential details are blurred!  I resized my images
-down to 512x512.
-You are welcome (and encouraged) to use the built-in
-dropout layer.

BYU CS classes

User Tools

Site Tools

Differences

Page Tools