From f111cb002b9c6065fdf6bb274ce5857a9e875e8c Mon Sep 17 00:00:00 2001
From: chenshijun <csj_sky@126.com>
Date: 星期三, 05 六月 2019 15:38:49 +0800
Subject: [PATCH] face rectangle
---
code/datasets.py | 435 ++++++++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 390 insertions(+), 45 deletions(-)
diff --git a/code/datasets.py b/code/datasets.py
index 63ee287..e8ab9f4 100644
--- a/code/datasets.py
+++ b/code/datasets.py
@@ -1,17 +1,84 @@
-import numpy as np
-import torch
-import cv2
-from torch.utils.data.dataset import Dataset
import os
-from PIL import Image
+import numpy as np
+import cv2
+import pandas as pd
+
+import torch
+from torch.utils.data.dataset import Dataset
+from torchvision import transforms
+
+from PIL import Image, ImageFilter
import utils
-def stack_grayscale_tensor(tensor):
- tensor = torch.cat([tensor, tensor, tensor], 0)
- return tensor
+def get_list_from_filenames(file_path):
+ # input: relative path to .txt file with file names
+ # output: list of relative path names
+ with open(file_path) as f:
+ lines = f.read().splitlines()
+ return lines
+
+class Synhead(Dataset):
+ def __init__(self, data_dir, csv_path, transform, test=False):
+ column_names = ['path', 'bbox_x_min', 'bbox_y_min', 'bbox_x_max', 'bbox_y_max', 'yaw', 'pitch', 'roll']
+ tmp_df = pd.read_csv(csv_path, sep=',', names=column_names, index_col=False, encoding="utf-8-sig")
+ self.data_dir = data_dir
+ self.transform = transform
+ self.X_train = tmp_df['path']
+ self.y_train = tmp_df[['bbox_x_min', 'bbox_y_min', 'bbox_x_max', 'bbox_y_max', 'yaw', 'pitch', 'roll']]
+ self.length = len(tmp_df)
+ self.test = test
+
+ def __getitem__(self, index):
+ path = os.path.join(self.data_dir, self.X_train.iloc[index]).strip('.jpg') + '.png'
+ img = Image.open(path)
+ img = img.convert('RGB')
+
+ x_min, y_min, x_max, y_max, yaw, pitch, roll = self.y_train.iloc[index]
+ x_min = float(x_min); x_max = float(x_max)
+ y_min = float(y_min); y_max = float(y_max)
+ yaw = -float(yaw); pitch = float(pitch); roll = float(roll)
+
+ # 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)
+
+ width, height = img.size
+ # Crop the face
+ 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)
+
+ # 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
+
+ labels = torch.LongTensor(binned_pose)
+ 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):
+ return self.length
class Pose_300W_LP(Dataset):
+ # Head pose from 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
@@ -29,20 +96,20 @@
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
+ # Crop the face loosely
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)
+ # 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
@@ -51,19 +118,106 @@
pitch = pose[0] * 180 / np.pi
yaw = pose[1] * 180 / np.pi
roll = pose[2] * 180 / np.pi
+
+ # 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))
+ # Get target tensors
+ labels = binned_pose
+ cont_labels = torch.FloatTensor([yaw, pitch, roll])
if self.transform is not None:
img = self.transform(img)
- return img, labels, self.X_train[index]
+ return img, labels, cont_labels, self.X_train[index]
+
+ def __len__(self):
+ # 122,450
+ return self.length
+
+class Pose_300W_LP_random_ds(Dataset):
+ # 300W-LP dataset with random downsampling
+ 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 loosely
+ 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)
+ pitch = pose[0] * 180 / np.pi
+ yaw = pose[1] * 180 / np.pi
+ roll = pose[2] * 180 / np.pi
+
+ ds = 1 + np.random.randint(0,4) * 5
+ 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 target tensors
+ labels = binned_pose
+ 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
@@ -88,18 +242,19 @@
img = img.convert(self.image_mode)
mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext)
- # Crop the face
+ # Crop the face loosely
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)
+ 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)))
# We get the pose in radians
@@ -111,14 +266,128 @@
# 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, self.X_train[index]
+ return img, labels, cont_labels, self.X_train[index]
def __len__(self):
# 2,000
+ return self.length
+
+class AFLW2000_ds(Dataset):
+ # AFLW2000 dataset with fixed downsampling
+ 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 loosely
+ 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 = 3 # downsampling factor
+ 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)
+ # 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 AFLW_aug(Dataset):
+ # AFLW dataset with flipping
+ 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):
+ img = Image.open(os.path.join(self.data_dir, self.X_train[index] + 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 radians
+ annot = open(txt_path, 'r')
+ line = annot.readline().split(' ')
+ pose = [float(line[1]), float(line[2]), float(line[3])]
+ # And convert to degrees.
+ yaw = pose[0] * 180 / np.pi
+ pitch = pose[1] * 180 / np.pi
+ roll = pose[2] * 180 / np.pi
+ # Fix the roll in AFLW
+ roll *= -1
+
+ # Augment
+ # 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))
+ 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):
+ # train: 18,863
+ # test: 1,966
return self.length
class AFLW(Dataset):
@@ -148,17 +417,17 @@
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
+ # Fix the roll in AFLW
+ roll *= -1
# 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, self.X_train[index]
+ return img, labels, cont_labels, self.X_train[index]
def __len__(self):
# train: 18,863
@@ -192,32 +461,108 @@
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
+ # Crop the face loosely
+ k = 0.32
+ x1 = float(line[4])
+ y1 = float(line[5])
+ x2 = float(line[6])
+ y2 = float(line[7])
+ x1 -= 0.8 * k * abs(x2 - x1)
+ y1 -= 2 * k * abs(y2 - y1)
+ x2 += 0.8 * k * abs(x2 - x1)
+ y2 += 1 * k * abs(y2 - y1)
- img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max)))
+ img = img.crop((int(x1), int(y1), int(x2), int(y2)))
# 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, self.X_train[index]
+ return img, labels, cont_labels, self.X_train[index]
def __len__(self):
# Around 200
return self.length
+class BIWI(Dataset):
+ def __init__(self, data_dir, filename_path, transform, img_ext='.png', annot_ext='.txt', image_mode='RGB'):
+ self.data_dir = data_dir
+ self.transform = transform
+ self.img_ext = img_ext
+ self.annot_ext = annot_ext
-def get_list_from_filenames(file_path):
- # input: relative path to .txt file with file names
- # output: list of relative path names
- with open(file_path) as f:
- lines = f.read().splitlines()
- return lines
+ 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] + '_rgb' + self.img_ext))
+ img = img.convert(self.image_mode)
+ pose_path = os.path.join(self.data_dir, self.y_train[index] + '_pose' + self.annot_ext)
+
+ y_train_list = self.y_train[index].split('/')
+ bbox_path = os.path.join(self.data_dir, y_train_list[0] + '/dockerface-' + y_train_list[-1] + '_rgb' + self.annot_ext)
+
+ # Load bounding box
+ bbox = open(bbox_path, 'r')
+ line = bbox.readline().split(' ')
+ if len(line) < 4:
+ x_min, y_min, x_max, y_max = 0, 0, img.size[0], img.size[1]
+ else:
+ x_min, y_min, x_max, y_max = [float(line[1]), float(line[2]), float(line[3]), float(line[4])]
+ bbox.close()
+
+ # Load pose in degrees
+ pose_annot = open(pose_path, 'r')
+ R = []
+ for line in pose_annot:
+ line = line.strip('\n').split(' ')
+ l = []
+ if line[0] != '':
+ for nb in line:
+ if nb == '':
+ continue
+ l.append(float(nb))
+ R.append(l)
+
+ R = np.array(R)
+ T = R[3,:]
+ R = R[:3,:]
+ pose_annot.close()
+
+ R = np.transpose(R)
+
+ 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
+
+ # Loosely crop face
+ k = 0.35
+ x_min -= 0.6 * k * abs(x_max - x_min)
+ y_min -= 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)))
+
+ # Bin values
+ bins = np.array(range(-99, 102, 3))
+ binned_pose = np.digitize([yaw, pitch, roll], bins) - 1
+
+ labels = torch.LongTensor(binned_pose)
+ 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):
+ # 15,667
+ return self.length
--
Gitblit v1.8.0