From e306e86e925e4211c1c2d2f68de45d5e55f3e215 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期日, 13 八月 2017 01:22:31 +0800
Subject: [PATCH] Some cleanup and AFLW working
---
code/datasets.py | 124 +++++++++++++++++++++++++----------------
1 files changed, 75 insertions(+), 49 deletions(-)
diff --git a/code/datasets.py b/code/datasets.py
index 3750e71..4cd8449 100644
--- a/code/datasets.py
+++ b/code/datasets.py
@@ -7,8 +7,12 @@
import utils
-class Pose_300W_LP(Dataset):
- def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
+def stack_grayscale_tensor(tensor):
+ tensor = torch.cat([tensor, tensor, tensor], 0)
+ return tensor
+
+class 300W_LP(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
self.img_ext = img_ext
@@ -18,26 +22,55 @@
self.X_train = filename_list
self.y_train = filename_list
+ self.image_mode = image_mode
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')
+ img = img.convert(self.image_mode)
+ mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
+ shape_path = os.path.join(self.data_dir, self.y_train[index] + '_shape.npy')
- pose = utils.get_ypr_from_mat(os.path.join(self.data_dir, self.y_train[index] + self.annot_ext))
- label = torch.FloatTensor(pose)
+ # Crop the face
+ pt2d = utils.get_pt2d_from_mat(mat_path)
+ x_min = min(pt2d[0,:])
+ y_min = min(pt2d[1,:])
+ x_max = max(pt2d[0,:])
+ y_max = max(pt2d[1,:])
+
+ k = 0.15
+ x_min -= k * abs(x_max - x_min)
+ y_min -= 4 * k * abs(y_max - y_min)
+ x_max += k * abs(x_max - x_min)
+ y_max += 0.4 * k * abs(y_max - y_min)
+ img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
+
+ # We get the pose in radians
+ pose = utils.get_ypr_from_mat(mat_path)
+ # And convert to degrees.
+ pitch = pose[0] * 180 / np.pi
+ yaw = pose[1] * 180 / np.pi
+ roll = pose[2] * 180 / np.pi
+ # Bin values
+ bins = np.array(range(-99, 102, 3))
+ binned_pose = np.digitize([yaw, pitch, roll], bins) - 1
+
+ # Get shape
+ shape = np.load(shape_path)
+
+ labels = torch.LongTensor(np.concatenate((binned_pose, shape), axis = 0))
if self.transform is not None:
img = self.transform(img)
- return img, label, self.X_train[index]
+ return img, labels, 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'):
+ 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
self.img_ext = img_ext
@@ -47,43 +80,30 @@
self.X_train = filename_list
self.y_train = filename_list
+ self.image_mode = image_mode
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')
+ img = img.convert(self.image_mode)
+ mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
- pose = utils.get_ypr_from_mat(os.path.join(self.data_dir, self.y_train[index] + self.annot_ext))
- label = torch.FloatTensor(pose)
+ # Crop the face
+ pt2d = utils.get_pt2d_from_mat(mat_path)
+ x_min = min(pt2d[0,:])
+ y_min = min(pt2d[1,:])
+ x_max = max(pt2d[0,:])
+ y_max = max(pt2d[1,:])
- 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'):
- 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')
+ k = 0.15
+ x_min -= k * abs(x_max - x_min)
+ y_min -= 4 * k * abs(y_max - y_min)
+ x_max += k * abs(x_max - x_min)
+ y_max += 0.4 * k * abs(y_max - y_min)
+ img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
# We get the pose in radians
- pose = utils.get_ypr_from_mat(os.path.join(self.data_dir, self.y_train[index] + self.annot_ext))
+ pose = utils.get_ypr_from_mat(mat_path)
# And convert to degrees.
pitch = pose[0] * 180 / np.pi
yaw = pose[1] * 180 / np.pi
@@ -98,11 +118,11 @@
return img, labels, self.X_train[index]
def __len__(self):
- # 122,450
+ # 2,000
return self.length
-class AFLW2000_binned(Dataset):
- def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat'):
+class AFLW(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
@@ -112,31 +132,37 @@
self.X_train = filename_list
self.y_train = filename_list
+ self.image_mode = image_mode
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')
+ 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 radians
- pose = utils.get_ypr_from_mat(os.path.join(self.data_dir, self.y_train[index] + self.annot_ext))
+ annot = open(txt_path, 'r')
+ line = annot.readline().split(' ')
+ pose = [float(line[1]), float(line[2]), float(line[3])]
# And convert to degrees.
- pitch, yaw, roll = pose * 180 / np.pi
+ 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))
- binned_pitch = torch.DoubleTensor(np.digitize(pitch, bins) - 1)
- binned_yaw = torch.DoubleTensor(np.digitize(yaw, bins) - 1)
- binned_roll = torch.DoubleTensor(np.digitize(roll, bins) - 1)
-
- label = binned_yaw, binned_pitch, binned_roll
+ labels = torch.LongTensor(np.digitize([yaw, pitch, roll], bins) - 1)
if self.transform is not None:
img = self.transform(img)
- return img, label, self.X_train[index]
+ return img, labels, self.X_train[index]
def __len__(self):
- # 2,000
+ # train: 18,863
+ # test: 1,966
return self.length
def get_list_from_filenames(file_path):
--
Gitblit v1.8.0