From 43416c4717d2430c3e11f042294d12b781fee2e1 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期三, 27 九月 2017 04:09:30 +0800
Subject: [PATCH] Failed lstm experiment
---
code/datasets.py | 231 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 227 insertions(+), 4 deletions(-)
diff --git a/code/datasets.py b/code/datasets.py
index 17f1899..f5941ae 100644
--- a/code/datasets.py
+++ b/code/datasets.py
@@ -6,6 +6,7 @@
from PIL import Image, ImageFilter
import utils
+from torchvision import transforms
def stack_grayscale_tensor(tensor):
tensor = torch.cat([tensor, tensor, tensor], 0)
@@ -80,6 +81,168 @@
img = self.transform(img)
return img, labels, cont_labels, self.X_train[index]
+
+ def __len__(self):
+ # 122,450
+ return self.length
+
+class Pose_300W_LP_random_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)
+ shape_path = os.path.join(self.data_dir, self.y_train[index] + '_shape.npy')
+
+ # 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 = 0.2 to 0.40
+ k = np.random.random_sample() * 0.2 + 0.2
+ x_min -= 0.6 * 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)
+ 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
+
+ rnd = np.random.random_sample()
+ if rnd < 0.5:
+ ds = 10
+ original_size = img.size
+ img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=Image.NEAREST)
+ img = img.resize((original_size[0], original_size[1]), resample=Image.NEAREST)
+
+ # Flip?
+ rnd = np.random.random_sample()
+ if rnd < 0.5:
+ yaw = -yaw
+ roll = -roll
+ img = img.transpose(Image.FLIP_LEFT_RIGHT)
+
+ # Blur?
+ rnd = np.random.random_sample()
+ if rnd < 0.05:
+ img = img.filter(ImageFilter.BLUR)
+
+ # 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))
+ 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):
+ # 122,450
+ return self.length
+
+class Pose_300W_LP_SR(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 = 0.2 to 0.40
+ k = np.random.random_sample() * 0.2 + 0.2
+ x_min -= 0.6 * 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)
+ 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
+
+ rnd = np.random.random_sample()
+ if rnd < 0.5:
+ ds = 10
+ original_size = img.size
+ img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=Image.NEAREST)
+ img = img.resize((original_size[0], original_size[1]), resample=Image.NEAREST)
+
+ # Flip?
+ rnd = np.random.random_sample()
+ if rnd < 0.5:
+ yaw = -yaw
+ roll = -roll
+ img = img.transpose(Image.FLIP_LEFT_RIGHT)
+
+ # Blur?
+ rnd = np.random.random_sample()
+ if rnd < 0.05:
+ img = img.filter(ImageFilter.BLUR)
+
+ img_ycc = img.convert('YCbCr')
+
+ # Bin values
+ bins = np.array(range(-99, 102, 3))
+ binned_pose = np.digitize([yaw, pitch, roll], bins) - 1
+
+ labels = torch.LongTensor(np.concatenate((binned_pose, shape), axis = 0))
+ cont_labels = torch.FloatTensor([yaw, pitch, roll])
+
+ # Transforms
+ img = transforms.Scale(240)(img)
+ img = transforms.RandomCrop(224)(img)
+ img_ycc = img.convert('YCbCr')
+ img = transforms.ToTensor()
+ img_ycc = transforms.ToTensor()
+
+ return img, img_ycc, labels, cont_labels, self.X_train[index]
def __len__(self):
# 122,450
@@ -172,10 +335,70 @@
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
+ ds = 8
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)
+ img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=Image.NEAREST)
+ img = img.resize((original_size[0], original_size[1]), resample=Image.NEAREST)
+
+ # 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_random_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)))
+
+ rnd = np.random.random_sample()
+ if rnd < 0.5:
+ ds = 10
+ original_size = img.size
+ img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=Image.NEAREST)
+ img = img.resize((original_size[0], original_size[1]), resample=Image.NEAREST)
# We get the pose in radians
pose = utils.get_ypr_from_mat(mat_path)
@@ -412,7 +635,7 @@
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
--
Gitblit v1.8.0