in py2/train.py [0:0]
def test(epoch, niter):
def truths_length(truths):
for i in range(50):
if truths[i][1] == 0:
return i
# Set the module in evaluation mode (turn off dropout, batch normalization etc.)
model.eval()
# Parameters
num_classes = model.num_classes
anchors = model.anchors
num_anchors = model.num_anchors
testtime = True
testing_error_trans = 0.0
testing_error_angle = 0.0
testing_error_pixel = 0.0
testing_samples = 0.0
errs_2d = []
errs_3d = []
errs_trans = []
errs_angle = []
errs_corner2D = []
logging(" Testing...")
logging(" Number of test samples: %d" % len(test_loader.dataset))
notpredicted = 0
# Iterate through test examples
for batch_idx, (data, target) in enumerate(test_loader):
t1 = time.time()
# Pass the data to GPU
if use_cuda:
data = data.cuda()
target = target.cuda()
# Wrap tensors in Variable class, set volatile=True for inference mode and to use minimal memory during inference
data = Variable(data, volatile=True)
t2 = time.time()
# Formward pass
output = model(data).data
t3 = time.time()
# Using confidence threshold, eliminate low-confidence predictions
all_boxes = get_region_boxes(output, conf_thresh, num_classes, anchors, num_anchors)
t4 = time.time()
# Iterate through all batch elements
for i in range(output.size(0)):
# For each image, get all the predictions
boxes = all_boxes[i]
# For each image, get all the targets (for multiple object pose estimation, there might be more than 1 target per image)
truths = target[i].view(-1, 21)
# Get how many object are present in the scene
num_gts = truths_length(truths)
# Iterate through each ground-truth object
for k in range(num_gts):
box_gt = [truths[k][1], truths[k][2], truths[k][3], truths[k][4], truths[k][5], truths[k][6],
truths[k][7], truths[k][8], truths[k][9], truths[k][10], truths[k][11], truths[k][12],
truths[k][13], truths[k][14], truths[k][15], truths[k][16], truths[k][17], truths[k][18], 1.0, 1.0, truths[k][0]]
best_conf_est = -1
# If the prediction has the highest confidence, choose it as our prediction
for j in range(len(boxes)):
if boxes[j][18] > best_conf_est:
best_conf_est = boxes[j][18]
box_pr = boxes[j]
match = corner_confidence9(box_gt[:18], torch.FloatTensor(boxes[j][:18]))
# Denormalize the corner predictions
corners2D_gt = np.array(np.reshape(box_gt[:18], [9, 2]), dtype='float32')
corners2D_pr = np.array(np.reshape(box_pr[:18], [9, 2]), dtype='float32')
corners2D_gt[:, 0] = corners2D_gt[:, 0] * im_width
corners2D_gt[:, 1] = corners2D_gt[:, 1] * im_height
corners2D_pr[:, 0] = corners2D_pr[:, 0] * im_width
corners2D_pr[:, 1] = corners2D_pr[:, 1] * im_height
# Compute corner prediction error
corner_norm = np.linalg.norm(corners2D_gt - corners2D_pr, axis=1)
corner_dist = np.mean(corner_norm)
errs_corner2D.append(corner_dist)
# Compute [R|t] by pnp
R_gt, t_gt = pnp(np.array(np.transpose(np.concatenate((np.zeros((3, 1)), corners3D[:3, :]), axis=1)), dtype='float32'), corners2D_gt, np.array(internal_calibration, dtype='float32'))
R_pr, t_pr = pnp(np.array(np.transpose(np.concatenate((np.zeros((3, 1)), corners3D[:3, :]), axis=1)), dtype='float32'), corners2D_pr, np.array(internal_calibration, dtype='float32'))
# Compute errors
# Compute translation error
trans_dist = np.sqrt(np.sum(np.square(t_gt - t_pr)))
errs_trans.append(trans_dist)
# Compute angle error
angle_dist = calcAngularDistance(R_gt, R_pr)
errs_angle.append(angle_dist)
# Compute pixel error
Rt_gt = np.concatenate((R_gt, t_gt), axis=1)
Rt_pr = np.concatenate((R_pr, t_pr), axis=1)
proj_2d_gt = compute_projection(vertices, Rt_gt, internal_calibration)
proj_2d_pred = compute_projection(vertices, Rt_pr, internal_calibration)
norm = np.linalg.norm(proj_2d_gt - proj_2d_pred, axis=0)
pixel_dist = np.mean(norm)
errs_2d.append(pixel_dist)
# Compute 3D distances
transform_3d_gt = compute_transformation(vertices, Rt_gt)
transform_3d_pred = compute_transformation(vertices, Rt_pr)
norm3d = np.linalg.norm(transform_3d_gt - transform_3d_pred, axis=0)
vertex_dist = np.mean(norm3d)
errs_3d.append(vertex_dist)
# Sum errors
testing_error_trans += trans_dist
testing_error_angle += angle_dist
testing_error_pixel += pixel_dist
testing_samples += 1
t5 = time.time()
# Compute 2D projection, 6D pose and 5cm5degree scores
px_threshold = 5
acc = len(np.where(np.array(errs_2d) <= px_threshold)[0]) * 100. / (len(errs_2d)+eps)
acc3d = len(np.where(np.array(errs_3d) <= vx_threshold)[0]) * 100. / (len(errs_3d)+eps)
acc5cm5deg = len(np.where((np.array(errs_trans) <= 0.05) & (np.array(errs_angle) <= 5))[0]) * 100. / (len(errs_trans)+eps)
corner_acc = len(np.where(np.array(errs_corner2D) <= px_threshold)[0]) * 100. / (len(errs_corner2D)+eps)
mean_err_2d = np.mean(errs_2d)
mean_corner_err_2d = np.mean(errs_corner2D)
nts = float(testing_samples)
if testtime:
print('-----------------------------------')
print(' tensor to cuda : %f' % (t2 - t1))
print(' predict : %f' % (t3 - t2))
print('get_region_boxes : %f' % (t4 - t3))
print(' eval : %f' % (t5 - t4))
print(' total : %f' % (t5 - t1))
print('-----------------------------------')
# Print test statistics
logging(" Mean corner error is %f" % (mean_corner_err_2d))
logging(' Acc using {} px 2D Projection = {:.2f}%'.format(px_threshold, acc))
logging(' Acc using {} vx 3D Transformation = {:.2f}%'.format(vx_threshold, acc3d))
logging(' Acc using 5 cm 5 degree metric = {:.2f}%'.format(acc5cm5deg))
logging(' Translation error: %f, angle error: %f' % (testing_error_trans/(nts+eps), testing_error_angle/(nts+eps)) )
# Register losses and errors for saving later on
testing_iters.append(niter)
testing_errors_trans.append(testing_error_trans/(nts+eps))
testing_errors_angle.append(testing_error_angle/(nts+eps))
testing_errors_pixel.append(testing_error_pixel/(nts+eps))
testing_accuracies.append(acc)