File size: 2,645 Bytes
092fe0d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import pandas as pd
import numpy as np
from torch.utils.data import Dataset
import os
from PIL import Image
class Thyroid_Datasets(Dataset):
def __init__(
self,
path_to_images,
fold,
PRED_LABEL,
transform=None,
sample=0,
finding="any"):
self.transform = transform
self.path_to_images = path_to_images
self.PRED_LABEL = PRED_LABEL
self.df = pd.read_csv("%s/CSV/%s.csv" % (path_to_images,fold))
print("%s/CSV/%s.csv " % (path_to_images,fold), "num of images: %s" % len(self.df))
if(sample > 0 and sample < len(self.df)):
self.df = self.df.sample(sample)
self.df = self.df.dropna(subset = ['Path'])
self.df = self.df.set_index("Path")
def __len__(self):
return len(self.df)
def __getitem__(self, idx):
X = self.df.index[idx]
if str(X) is not None:
image = Image.open(os.path.join(self.path_to_images,str(X)))
image = image.convert('RGB')
label = self.df["label".strip()].iloc[idx].astype('int')
subg = self.df["subtype".strip()].iloc[idx]
if self.transform:
image = self.transform(image)
return (image, label, subg)
class Multi_Thyroid_Datasets(Dataset):
def __init__(
self,
path_to_images,
fold,
PRED_LABEL,
transform=None,
sample=0,
finding="any"):
self.transform = transform
self.path_to_images = path_to_images
self.PRED_LABEL = PRED_LABEL
self.df = pd.read_csv("%s/CSV/%s.csv" % (path_to_images,fold))
print("%s/CSV/%s.csv " % (path_to_images,fold), "num of images: %s" % len(self.df))
if(sample > 0 and sample < len(self.df)):
self.df = self.df.sample(sample)
self.df = self.df.dropna(subset = ['Path'])
self.df = self.df.set_index("Path")
def __len__(self):
return len(self.df)
def __getitem__(self, idx):
X = self.df.index[idx]
if str(X) is not None:
image = Image.open(os.path.join(self.path_to_images,str(X)))
image = image.convert('RGB')
label = self.df["label".strip()].iloc[idx].astype('int')
subg = self.df["subtype".strip()].iloc[idx]
if self.transform:
image = self.transform(image)
return (image, label, subg)
return (image, label, subg) |