From 18a21d4b07c581a8954b08518115fb035c712b28 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期二, 08 八月 2017 07:34:09 +0800
Subject: [PATCH] Added new correct cropping for training and smoothing for video.
---
code/test_resnet_bins.py | 46 ++++++++++++++++++++++++++++++++++------------
1 files changed, 34 insertions(+), 12 deletions(-)
diff --git a/code/test_resnet_bins.py b/code/test_resnet_bins.py
index f5be4f8..00d2109 100644
--- a/code/test_resnet_bins.py
+++ b/code/test_resnet_bins.py
@@ -31,6 +31,8 @@
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)
args = parser.parse_args()
@@ -44,8 +46,12 @@
gpu = args.gpu_id
snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
- # ResNet50 with 3 outputs.
- model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66)
+ # 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)
+ # ResNet18
+ model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
print 'Loading snapshot.'
# Load snapshot
@@ -84,38 +90,54 @@
for i, (images, labels, name) in enumerate(test_loader):
images = Variable(images).cuda(gpu)
-
total += labels.size(0)
label_yaw = labels[:,0]
label_pitch = labels[:,1]
label_roll = labels[:,2]
yaw, pitch, roll = model(images)
- # _, yaw_predicted = torch.max(yaw.data, 1)
- # _, pitch_predicted = torch.max(pitch.data, 1)
- # _, roll_predicted = torch.max(roll.data, 1)
+
+ # Binned predictions
+ _, yaw_bpred = torch.max(yaw.data, 1)
+ _, pitch_bpred = torch.max(pitch.data, 1)
+ _, roll_bpred = torch.max(roll.data, 1)
yaw_predicted = F.softmax(yaw)
pitch_predicted = F.softmax(pitch)
roll_predicted = F.softmax(roll)
+ # Continuous predictions
yaw_predicted = torch.sum(yaw_predicted.data[0] * idx_tensor)
pitch_predicted = torch.sum(pitch_predicted.data[0] * idx_tensor)
roll_predicted = torch.sum(roll_predicted.data[0] * idx_tensor)
+ # Mean absolute error
yaw_error += abs(yaw_predicted - label_yaw[0]) * 3
pitch_error += abs(pitch_predicted - label_pitch[0]) * 3
roll_error += abs(roll_predicted - label_roll[0]) * 3
- # for er in xrange(0,n_margins):
- # yaw_correct[er] += (label_yaw[0] in range(yaw_predicted[0,0] - er, yaw_predicted[0,0] + er + 1))
- # pitch_correct[er] += (label_pitch[0] in range(pitch_predicted[0,0] - er, pitch_predicted[0,0] + er + 1))
- # roll_correct[er] += (label_roll[0] in range(roll_predicted[0,0] - er, roll_predicted[0,0] + er + 1))
+ # Binned Accuracy
+ # for er in xrange(n_margins):
+ # yaw_bpred[er] += (label_yaw[0] in range(yaw_bpred[0,0] - er, yaw_bpred[0,0] + er + 1))
+ # pitch_bpred[er] += (label_pitch[0] in range(pitch_bpred[0,0] - er, pitch_bpred[0,0] + er + 1))
+ # roll_bpred[er] += (label_roll[0] in range(roll_bpred[0,0] - er, roll_bpred[0,0] + er + 1))
- # print label_yaw[0], yaw_predicted[0,0]
- # 4 -> 15
+ # print label_yaw[0], yaw_bpred[0,0]
+
+ # Save images with pose cube.
+ if args.save_viz:
+ name = name[0]
+ cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
+ #print os.path.join('output/images', name + '.jpg')
+ #print label_yaw[0] * 3 - 99, label_pitch[0] * 3 - 99, label_roll[0] * 3 - 99
+ #print yaw_predicted * 3 - 99, pitch_predicted * 3 - 99, roll_predicted * 3 - 99
+ utils.plot_pose_cube(cv2_img, yaw_predicted * 3 - 99, pitch_predicted * 3 - 99, roll_predicted * 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