From 888dc776c36f9e1f8803732c34dfc359ad81dcee Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期三, 29 十一月 2017 13:11:42 +0800
Subject: [PATCH] Synhead
---
code/datasets.py | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 60 insertions(+), 0 deletions(-)
diff --git a/code/datasets.py b/code/datasets.py
index a28c584..5f1dfdc 100644
--- a/code/datasets.py
+++ b/code/datasets.py
@@ -1,6 +1,7 @@
import os
import numpy as np
import cv2
+import pandas as pd
import torch
from torch.utils.data.dataset import Dataset
@@ -17,6 +18,65 @@
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'):
--
Gitblit v1.8.0