From b74b9c54247177c82493f180617d7551de8e2bb1 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期二, 26 九月 2017 03:47:06 +0800
Subject: [PATCH] Before SR experiments
---
code/datasets.py | 74 +++++++++++++++++++++++++++++++-----
1 files changed, 63 insertions(+), 11 deletions(-)
diff --git a/code/datasets.py b/code/datasets.py
index 5825105..17f1899 100644
--- a/code/datasets.py
+++ b/code/datasets.py
@@ -106,17 +106,76 @@
# 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 -= 0.6 * k * abs(x_max - x_min)
+ k = 0.20
+ x_min -= 2 * k * abs(x_max - x_min)
y_min -= 2 * k * abs(y_max - y_min)
- x_max += 0.6 * k * abs(x_max - x_min)
+ x_max += 2 * k * abs(x_max - x_min)
y_max += 0.6 * 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))
+ labels = torch.LongTensor(np.digitize([yaw, pitch, roll], bins) - 1)
+ cont_labels = torch.FloatTensor([yaw, pitch, roll])
+
+ if self.transform is not None:
+ img = self.transform(img)
+
+ return img, labels, cont_labels, self.X_train[index]
+
+ def __len__(self):
+ # 2,000
+ return self.length
+
+class AFLW2000_ds(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
+ 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):
+ img = Image.open(os.path.join(self.data_dir, self.X_train[index] + self.img_ext))
+ img = img.convert(self.image_mode)
+ mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
+
+ # 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 = 0.20
+ x_min -= 2 * k * abs(x_max - x_min)
+ y_min -= 2 * k * abs(y_max - y_min)
+ x_max += 2 * k * abs(x_max - x_min)
+ y_max += 0.6 * k * abs(y_max - y_min)
+ img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
+
+ ds = 5
+ original_size = img.size
+ img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=0)
+ img = img.resize((original_size[0], original_size[1]), resample=0)
# We get the pose in radians
pose = utils.get_ypr_from_mat(mat_path)
@@ -353,7 +412,7 @@
R = R[:3,:]
pose_annot.close()
- roll = np.arctan2(R[1][0], R[0][0]) * 180 / np.pi
+ roll = -np.arctan2(R[1][0], R[0][0]) * 180 / np.pi
yaw = np.arctan2(-R[2][0], np.sqrt(R[2][1] ** 2 + R[2][2] ** 2)) * 180 / np.pi
pitch = -np.arctan2(R[2][1], R[2][2]) * 180 / np.pi
@@ -364,13 +423,6 @@
x_max += 0.6 * k * abs(x_max - x_min)
y_max += 0.6 * k * abs(y_max - y_min)
img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
-
- # Flip?
- # rnd = np.random.random_sample()
- # if rnd < 0.5:
- # yaw = -yaw
- # roll = -roll
- # img = img.transpose(Image.FLIP_LEFT_RIGHT)
# Bin values
bins = np.array(range(-99, 102, 3))
--
Gitblit v1.8.0