def main():
opt = opts().parse()
model = torch.load(opt.loadModel)
img = cv2.imread(opt.demo)
s = max(img.shape[0], img.shape[1]) * 1.0
c = np.array([img.shape[1] / 2., img.shape[0] / 2.])
img = Crop(img, c, s, 0, ref.inputRes) / 256.
input = torch.from_numpy(img.copy()).float()
input = input.view(1, input.size(0), input.size(1), input.size(2))
input_var = torch.autograd.Variable(input).float()
if opt.GPU > -1:
model = model.cuda(opt.GPU)
input_var = input_var.cuda(opt.GPU)
output = model(input_var)
hm = output[-1].data.cpu().numpy()
debugger = Debugger()
img = (input[0].numpy().transpose(1, 2, 0) * 256).astype(np.uint8).copy()
inp = img.copy()
star = (cv2.resize(hm[0, 0], (ref.inputRes, ref.inputRes)) * 255)
star[star > 255] = 255
star[star < 0] = 0
star = np.tile(star, (3, 1, 1)).transpose(1, 2, 0)
trans = 0.8
star = (trans * star + (1. - trans) * img).astype(np.uint8)
ps = parseHeatmap(hm[0], thresh=0.1)
canonical, pred, color, score = [], [], [], []
for k in range(len(ps[0])):
x, y, z = ((hm[0, 1:4, ps[0][k], ps[1][k]] + 0.5) *
ref.outputRes).astype(np.int32)
dep = ((hm[0, 4, ps[0][k], ps[1][k]] + 0.5) * ref.outputRes).astype(
np.int32)
canonical.append([x, y, z])
pred.append([ps[1][k], ref.outputRes - dep, ref.outputRes - ps[0][k]])
score.append(hm[0, 0, ps[0][k], ps[1][k]])
color.append((1.0 * x / ref.outputRes, 1.0 * y / ref.outputRes,
1.0 * z / ref.outputRes))
cv2.circle(img, (ps[1][k] * 4, ps[0][k] * 4), 4, (255, 255, 255), -1)
cv2.circle(img, (ps[1][k] * 4, ps[0][k] * 4), 2,
(int(z * 4), int(y * 4), int(x * 4)), -1)
pred = np.array(pred).astype(np.float32)
canonical = np.array(canonical).astype(np.float32)
pointS = canonical * 1.0 / ref.outputRes
pointT = pred * 1.0 / ref.outputRes
R, t, s = horn87(pointS.transpose(), pointT.transpose(), score)
rotated_pred = s * np.dot(
R, canonical.transpose()).transpose() + t * ref.outputRes
debugger.addImg(inp, 'inp')
debugger.addImg(star, 'star')
debugger.addImg(img, 'nms')
debugger.addPoint3D(canonical / ref.outputRes - 0.5, c=color, marker='^')
debugger.addPoint3D(pred / ref.outputRes - 0.5, c=color, marker='x')
debugger.addPoint3D(rotated_pred / ref.outputRes - 0.5,
c=color,
marker='*')
debugger.showAllImg(pause=True)
debugger.show3D()
def main():
# use the model trained with dropout enabled
model_path = '/home/erl/moshan/orcvio_gamma/orcvio_gamma/pytorch_models/starmap/trained_models/with_dropout/model_cpu.pth'
img_path = './images/car.png'
det_name = './det/car.png'
# by default img size is 256
inputRes = 256
outputRes = 64
CUDA = torch.cuda.is_available()
model = torch.load(model_path)
img = cv2.imread(img_path)
s = max(img.shape[0], img.shape[1]) * 1.0
c = np.array([img.shape[1] / 2., img.shape[0] / 2.])
# img = cv2.resize(img, (320, 240))
# print(img.shape)
# crop only change h, w, c to c, h, w for images with size 256 x 256
img = Crop(img, c, s, 0, inputRes).astype(np.float32).transpose(2, 0,
1) / 256.
input = torch.from_numpy(img.copy()).float()
# change to b, c, h, w
input = input.view(1, input.size(0), input.size(1), input.size(2))
input_var = torch.autograd.Variable(input).float()
if CUDA:
model.cuda()
input_var = input_var.cuda()
output = model(input_var)
hm = output[-1].data.cpu().numpy()
# convert to bgr, uint8 for display
img = (input[0].numpy().transpose(1, 2, 0) * 256).astype(np.uint8).copy()
inp = img.copy()
# hm[0, 0] is an image, since 1st dim is batch
star = (cv2.resize(hm[0, 0], (inputRes, inputRes)) * 255)
# clip the values to 0-255
star[star > 255] = 255
star[star < 0] = 0
# tile Construct an array by repeating A the number of times given by reps.
# convert to 3 channels, for bgr
star = np.tile(star, (3, 1, 1)).transpose(1, 2, 0)
trans = 0.8
star = (trans * star + (1. - trans) * img).astype(np.uint8)
# select peaks and perform nms
# set nms threshold
heat_thresh = 0.25
ps = parseHeatmap(hm[0], heat_thresh)
canonical, pred, color, score = [], [], [], []
# mc dropout
f1 = plt.figure()
ax1 = f1.add_subplot(111)
ax1.imshow(img)
uncertainty_test(model, input_var, heat_thresh, ax1)
for k in range(len(ps[0])):
# camviewfeature
x, y, z = ((hm[0, 1:4, ps[0][k], ps[1][k]] + 0.5) * outputRes).astype(
np.int32)
dep = ((hm[0, 4, ps[0][k], ps[1][k]] + 0.5) * outputRes).astype(
np.int32)
canonical.append([x, y, z])
pred.append([ps[1][k], outputRes - dep, outputRes - ps[0][k]])
# kp confidence score
score.append(hm[0, 0, ps[0][k], ps[1][k]])
color.append(
(1.0 * x / outputRes, 1.0 * y / outputRes, 1.0 * z / outputRes))
# cv2.circle(img, center, radius, color[, thickness[, lineType[, shift]]]) → img
# -1 means that a filled circle is to be drawn
cv2.circle(img, (ps[1][k] * 4, ps[0][k] * 4), 6, (0, 0, 255), -1)
cv2.circle(img, (ps[1][k] * 4, ps[0][k] * 4), 2,
(int(z * 4), int(y * 4), int(x * 4)), -1)
# plot cov
# pos = kps_mean[k]
# covar = kps_cov[k]
# draw_ellipse(pos, covar, ax1)
plt.axis('off')
ax1.get_xaxis().set_visible(False)
ax1.get_yaxis().set_visible(False)
plt.show()
f1.savefig('kp_cov.png', bbox_inches='tight', pad_inches=0)
# plt.pause(5)
pred = np.array(pred).astype(np.float32)
canonical = np.array(canonical).astype(np.float32)
pointS = canonical * 1.0 / outputRes
pointT = pred * 1.0 / outputRes
# calculate viewpoint
R, t, s = horn87(pointS.transpose(), pointT.transpose(), score)
rotated_pred = s * np.dot(
R, canonical.transpose()).transpose() + t * outputRes