def __getitem__(self, index):
item = self.records[index]
img = rio.load_site(item.dataset, item.experiment, item.plate, item.well, item.site, base_path=self.root)
label = item.sirna if self.mode == 'train' else item.id_code
out = self.transform(img, item.experiment)
if self.with_plates:
p = torch.zeros(4, dtype=torch.float32)
p[item.plate - 1] = 1.0
out = out, p
return out, label
def load_image(row):
images = []
for site in [1, 2]:
image = rio.load_site('train',
row['experiment'],
row['plate'],
row['well'],
site,
base_path=row['root'])
images.append(image)
images = np.stack(images, 0)
return images
# In[12]:
md['site'].value_counts()
# <strong>Image</strong>
# In[13]:
# pixel_stats.csv
# row 1-6
# train set, experiment HEPG2-01, plate 1, well B02, site 1
t = rio.load_site('train', 'HEPG2-01', 1, 'B02', 1, base_path=LOCAL_IMAGES_BASE_PATH)
t.shape
# In[14]:
img = t[:, :, 0] # channel 1
img.shape
# In[15]:
# In[3]:
# Ref:
# rxrx/io.py, line: 14, 15
LOCAL_IMAGES_BASE_PATH = 'D:\\_peng\\recursion-cellular-image-classification' # windows
DEFAULT_METADATA_BASE_PATH = LOCAL_IMAGES_BASE_PATH
# In[4]:
# train set, experiment RPE-05, plate 3, well D19, site 2
t = rio.load_site('train',
'RPE-05',
3,
'D19',
2,
base_path=LOCAL_IMAGES_BASE_PATH)
t.shape
# In[5]:
fig, axes = plt.subplots(2, 3, figsize=(24, 16))
for i, ax in enumerate(axes.flatten()):
ax.axis('off')
ax.set_title('channel {}'.format(i + 1))
_ = ax.imshow(t[:, :, i], cmap='gray')
# In[6]:
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import os
print(os.listdir("../input"))
import sys
import matplotlib.pyplot as plt
### matplotlib inline
### git clone https://github.com/recursionpharma/rxrx1-utils
print('rxrx1-utils cloned!')
### ls
sys.path.append('rxrx1-utils')
import rxrx.io as rio
t = rio.load_site('train', 'RPE-05', 3, 'D19', 2)
t.shape
fig, axes = plt.subplots(2, 3, figsize=(24, 16))
for i, ax in enumerate(axes.flatten()):
ax.axis('off')
ax.set_title('channel {}'.format(i + 1))
_ = ax.imshow(t[:, :, i], cmap='gray')
x = rio.convert_tensor_to_rgb(t)
x.shape
plt.figure(figsize=(8, 8))
plt.axis('off')
_ = plt.imshow(x)
y = rio.load_site_as_rgb('train', 'HUVEC-08', 4, 'K09', 1)
plt.figure(figsize=(8, 8))
plt.axis('off')