From 92ed4cb2ea68be44b1ff153e00410c2082ee62df Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期二, 15 八月 2017 00:28:28 +0800
Subject: [PATCH] New experiments with hourglass
---
code/datasets.py | 116 ++++++++++++++++++++++++++++------------------------------
1 files changed, 56 insertions(+), 60 deletions(-)
diff --git a/code/datasets.py b/code/datasets.py
index f6fcc45..63ee287 100644
--- a/code/datasets.py
+++ b/code/datasets.py
@@ -12,64 +12,6 @@
return tensor
class Pose_300W_LP(Dataset):
- def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
- self.data_dir = data_dir
- self.transform = transform
- self.img_ext = img_ext
- self.annot_ext = annot_ext
-
- filename_list = get_list_from_filenames(filename_path)
-
- self.X_train = filename_list
- self.y_train = filename_list
- self.length = len(filename_list)
-
- def __getitem__(self, index):
- img = Image.open(os.path.join(self.data_dir, self.X_train[index] + self.img_ext))
- img = img.convert('RGB')
-
- pose = utils.get_ypr_from_mat(os.path.join(self.data_dir, self.y_train[index] + self.annot_ext))
- label = torch.FloatTensor(pose)
-
- if self.transform is not None:
- img = self.transform(img)
-
- return img, label, self.X_train[index]
-
- def __len__(self):
- # 122,450
- return self.length
-
-class AFLW2000(Dataset):
- def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
- self.data_dir = data_dir
- self.transform = transform
- self.img_ext = img_ext
- self.annot_ext = annot_ext
-
- filename_list = get_list_from_filenames(filename_path)
-
- self.X_train = filename_list
- self.y_train = filename_list
- self.length = len(filename_list)
-
- def __getitem__(self, index):
- img = Image.open(os.path.join(self.data_dir, self.X_train[index] + self.img_ext))
- img = img.convert('RGB')
-
- pose = utils.get_ypr_from_mat(os.path.join(self.data_dir, self.y_train[index] + self.annot_ext))
- label = torch.FloatTensor(pose)
-
- if self.transform is not None:
- img = self.transform(img)
-
- return img, label, self.X_train[index]
-
- def __len__(self):
- # 2,000
- return self.length
-
-class Pose_300W_LP_binned(Dataset):
def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat', image_mode='RGB'):
self.data_dir = data_dir
self.transform = transform
@@ -127,7 +69,7 @@
# 122,450
return self.length
-class AFLW2000_binned(Dataset):
+class AFLW2000(Dataset):
def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat', image_mode='RGB'):
self.data_dir = data_dir
self.transform = transform
@@ -206,6 +148,9 @@
yaw = pose[0] * 180 / np.pi
pitch = pose[1] * 180 / np.pi
roll = pose[2] * 180 / np.pi
+ # Something weird with the roll in AFLW
+ if yaw < 0:
+ roll *= -1
# Bin values
bins = np.array(range(-99, 102, 3))
labels = torch.LongTensor(np.digitize([yaw, pitch, roll], bins) - 1)
@@ -216,9 +161,60 @@
return img, labels, self.X_train[index]
def __len__(self):
- # Check how many
+ # train: 18,863
+ # test: 1,966
return self.length
+class AFW(Dataset):
+ def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.txt', image_mode='RGB'):
+ self.data_dir = data_dir
+ self.transform = transform
+ self.img_ext = img_ext
+ self.annot_ext = annot_ext
+
+ filename_list = get_list_from_filenames(filename_path)
+
+ self.X_train = filename_list
+ self.y_train = filename_list
+ self.image_mode = image_mode
+ self.length = len(filename_list)
+
+ def __getitem__(self, index):
+ txt_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
+ img_name = self.X_train[index].split('_')[0]
+
+ img = Image.open(os.path.join(self.data_dir, img_name + self.img_ext))
+ img = img.convert(self.image_mode)
+ txt_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
+
+ # We get the pose in degrees
+ annot = open(txt_path, 'r')
+ line = annot.readline().split(' ')
+ yaw, pitch, roll = [float(line[1]), float(line[2]), float(line[3])]
+
+ # Crop the face
+ margin = 40
+ x_min = float(line[4]) - margin
+ y_min = float(line[5]) - margin
+ x_max = float(line[6]) + margin
+ y_max = float(line[7]) + margin
+
+ img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
+
+ # Bin values
+ bins = np.array(range(-99, 102, 3))
+ labels = torch.LongTensor(np.digitize([yaw, pitch, roll], bins) - 1)
+
+ if self.transform is not None:
+ img = self.transform(img)
+
+ return img, labels, self.X_train[index]
+
+ def __len__(self):
+ # Around 200
+ return self.length
+
+
def get_list_from_filenames(file_path):
# input: relative path to .txt file with file names
# output: list of relative path names
--
Gitblit v1.8.0