From dd62d6fa4a85f18a29de009a972f5599b19ec946 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期四, 14 九月 2017 00:51:53 +0800
Subject: [PATCH] Fixing hopenet
---
code/test.py | 91 ++++++++++++++++++++++++++++++++++++---------
1 files changed, 73 insertions(+), 18 deletions(-)
diff --git a/code/test.py b/code/test.py
index 401e02b..7f76714 100644
--- a/code/test.py
+++ b/code/test.py
@@ -5,6 +5,8 @@
from torch.utils.data import DataLoader
from torchvision import transforms
import torch.backends.cudnn as cudnn
+import torchvision
+import torch.nn.functional as F
import cv2
import matplotlib.pyplot as plt
@@ -12,7 +14,7 @@
import os
import argparse
-from datasets import AFLW2000
+import datasets
import hopenet
import utils
@@ -25,10 +27,14 @@
default='', type=str)
parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
default='', type=str)
- parser.add_argument('--snapshot', dest='snapshot', help='Name of model snapshot.',
+ parser.add_argument('--snapshot', dest='snapshot', help='Path of model snapshot.',
default='', type=str)
parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
default=1, type=int)
+ parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
+ default=False, type=bool)
+ parser.add_argument('--iter_ref', dest='iter_ref', default=1, type=int)
+ parser.add_argument('--dataset', dest='dataset', help='Dataset type.', default='AFLW2000', type=str)
args = parser.parse_args()
@@ -38,11 +44,15 @@
args = parse_args()
cudnn.enabled = True
- batch_size = 1
gpu = args.gpu_id
- snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
+ snapshot_path = args.snapshot
- model = hopenet.Simple_CNN()
+ # ResNet101 with 3 outputs.
+ # model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 23, 3], 66)
+ # ResNet50
+ model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, args.iter_ref)
+ # ResNet18
+ # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
print 'Loading snapshot.'
# Load snapshot
@@ -51,12 +61,24 @@
print 'Loading data.'
- transformations = transforms.Compose([transforms.Scale(302),transforms.CenterCrop(302),transforms.ToTensor()])
+ transformations = transforms.Compose([transforms.Scale(224),
+ transforms.CenterCrop(224), transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
- pose_dataset = AFLW2000(args.data_dir, args.filename_list,
+ if args.dataset == 'AFLW2000':
+ pose_dataset = datasets.AFLW2000(args.data_dir, args.filename_list,
transformations)
+ elif args.dataset == 'BIWI':
+ pose_dataset = datasets.BIWI(args.data_dir, args.filename_list, transformations)
+ elif args.dataset == 'AFLW':
+ pose_dataset = datasets.AFLW(args.data_dir, args.filename_list, transformations)
+ elif args.dataset == 'AFW':
+ pose_dataset = datasets.AFW(args.data_dir, args.filename_list, transformations)
+ else:
+ print 'Error: not a valid dataset name'
+ sys.exit()
test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
- batch_size=batch_size,
+ batch_size=args.batch_size,
num_workers=2)
model.cuda(gpu)
@@ -65,18 +87,51 @@
# Test the Model
model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
- error = .0
total = 0
- for i, (images, labels, path) in enumerate(test_loader):
+ n_margins = 20
+ yaw_correct = np.zeros(n_margins)
+ pitch_correct = np.zeros(n_margins)
+ roll_correct = np.zeros(n_margins)
+
+ idx_tensor = [idx for idx in xrange(66)]
+ idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
+
+ yaw_error = .0
+ pitch_error = .0
+ roll_error = .0
+
+ l1loss = torch.nn.L1Loss(size_average=False)
+
+ for i, (images, labels, name) in enumerate(test_loader):
images = Variable(images).cuda(gpu)
- labels = Variable(labels).cuda(gpu)
- outputs = model(images)
- _, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
- # TODO: There are more efficient ways.
- for idx in xrange(len(outputs)):
- error += utils.mse_loss(outputs[idx], labels[idx])
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
+ pre_yaw, pre_pitch, pre_roll, angles = model(images)
+ yaw = angles[args.iter_ref][:,0].cpu().data
+ pitch = angles[args.iter_ref][:,1].cpu().data
+ roll = angles[args.iter_ref][:,2].cpu().data
- print('Test MSE error of the model on the ' + str(total) +
- ' test images: %.4f' % (error / total))
+ # Mean absolute error
+ print yaw.numpy(), label_yaw.numpy()
+ yaw_error += torch.sum(torch.abs(yaw - label_yaw) * 3)
+ pitch_error += torch.sum(torch.abs(pitch - label_pitch) * 3)
+ roll_error += torch.sum(torch.abs(roll - label_roll) * 3)
+
+ # Save images with pose cube.
+ # TODO: fix for larger batch size
+ if args.save_viz:
+ name = name[0]
+ cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
+ utils.plot_pose_cube(cv2_img, yaw[0] * 3 - 99, pitch[0] * 3 - 99, roll[0] * 3 - 99)
+ cv2.imwrite(os.path.join('output/images', name + '.jpg'), cv2_img)
+
+ print('Test error in degrees of the model on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+
+ # Binned accuracy
+ # for idx in xrange(len(yaw_correct)):
+ # print yaw_correct[idx] / total, pitch_correct[idx] / total, roll_correct[idx] / total
--
Gitblit v1.8.0