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 | 103 ++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 81 insertions(+), 22 deletions(-)
diff --git a/code/test_resnet_bins.py b/code/test_resnet_bins.py
index 34fc8f5..699c9c9 100644
--- a/code/test_resnet_bins.py
+++ b/code/test_resnet_bins.py
@@ -6,6 +6,7 @@
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
@@ -13,7 +14,7 @@
import os
import argparse
-from datasets import AFLW2000
+import datasets
import hopenet
import utils
@@ -30,6 +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()
@@ -39,14 +42,15 @@
args = parse_args()
cudnn.enabled = True
- batch_size = 1
gpu = args.gpu_id
snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
- model = torchvision.models.resnet18()
- # Parameters of newly constructed modules have requires_grad=True by default
- num_ftrs = model.fc.in_features
- model.fc = nn.Linear(num_ftrs, 3)
+ # 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
@@ -55,12 +59,13 @@
print 'Loading data.'
- transformations = transforms.Compose([transforms.Scale(224),transforms.RandomCrop(224), transforms.ToTensor()])
+ transformations = transforms.Compose([transforms.Scale(224),
+ transforms.RandomCrop(224), transforms.ToTensor()])
- pose_dataset = AFLW2000(args.data_dir, args.filename_list,
+ 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)
@@ -69,22 +74,76 @@
# Test the Model
model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
- error = .0
total = 0
+ 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)):
- # if abs(outputs[idx].data[1] - labels[idx].data[1]) * 180 / np.pi > 30:
- print name
- print abs(outputs[idx].data - labels[idx].data) * 180 / np.pi, 180 * outputs[idx].data / np.pi, labels[idx].data * 180 / np.pi
- # error += utils.mse_loss(outputs[idx], labels[idx])
- error += abs(outputs[idx].data - labels[idx].data) * 180 / np.pi
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
+ yaw, pitch, roll = model(images)
- print('Test MSE error of the model on the ' + str(total) +
- ' test images: %.4f' % (error / total))
+ # 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 * idx_tensor, 1)
+ pitch_predicted = torch.sum(pitch_predicted.data * idx_tensor, 1)
+ roll_predicted = torch.sum(roll_predicted.data * idx_tensor, 1)
+
+ yaw_predicted = yaw_predicted.cpu()
+ pitch_predicted = pitch_predicted.cpu()
+ roll_predicted = roll_predicted.cpu()
+
+ # 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)
+
+ # 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_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