From 54818d253649ff588ed0054d10dabb2a3a170309 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期四, 10 八月 2017 04:08:12 +0800
Subject: [PATCH] Doing pretty well now with resnet50 and adam with low learning rate. Also fixed test script to use large batches.
---
code/test_resnet_bins.py | 71 ++++++++++++++++++++++++-----------
1 files changed, 48 insertions(+), 23 deletions(-)
diff --git a/code/test_resnet_bins.py b/code/test_resnet_bins.py
index 30aa158..699c9c9 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()
@@ -40,12 +42,14 @@
args = parse_args()
cudnn.enabled = True
- batch_size = 1
gpu = args.gpu_id
snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
- # ResNet50 with 3 outputs.
+ # 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.'
@@ -61,7 +65,7 @@
pose_dataset = datasets.AFLW2000_binned(args.data_dir, args.filename_list,
transformations)
test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
- batch_size=batch_size,
+ batch_size=args.batch_size,
num_workers=2)
model.cuda(gpu)
@@ -83,42 +87,63 @@
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)
-
total += labels.size(0)
- label_yaw = labels[:,0]
- label_pitch = labels[:,1]
- label_roll = labels[:,2]
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
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)
- 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)
+ # Continuous predictions
+ yaw_predicted = torch.sum(yaw_predicted.data * idx_tensor, 1)
+ pitch_predicted = torch.sum(pitch_predicted.data * idx_tensor, 1)
+ roll_predicted = torch.sum(roll_predicted.data * idx_tensor, 1)
- 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
+ yaw_predicted = yaw_predicted.cpu()
+ pitch_predicted = pitch_predicted.cpu()
+ roll_predicted = roll_predicted.cpu()
- # print yaw_predicted * 3, label_yaw[0] * 3, abs(yaw_predicted - label_yaw[0]) * 3
+ # Mean absolute error
+ yaw_error += torch.sum(torch.abs(yaw_predicted - label_yaw) * 3)
+ pitch_error += torch.sum(torch.abs(pitch_predicted - label_pitch) * 3)
+ roll_error += torch.sum(torch.abs(roll_predicted - label_roll) * 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.
+ # 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'))
+ #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[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[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