def process_image():
input_size = [512, 512]
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
dataset = SimpleFolderDataset(root=os.getcwd() + image_saved_path,
input_size=input_size,
transform=transform)
dataloader = DataLoader(dataset)
palette = get_palette(num_classes)
with torch.no_grad():
for idx, batch in enumerate(tqdm(dataloader)):
image, meta = batch
img_name = meta['name'][0]
c = meta['center'].numpy()[0]
s = meta['scale'].numpy()[0]
w = meta['width'].numpy()[0]
h = meta['height'].numpy()[0]
output = model(image.cuda())
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(output[0][-1][0].unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2, 0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
parsing_result_path = os.path.join(
os.getcwd() + process_image_path, img_name[:-4] + '.png')
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
output_img.putpalette(palette)
output_img.save(parsing_result_path)
def main():
args = get_arguments()
gpus = [int(i) for i in args.gpu.split(',')]
assert len(gpus) == 1
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
num_classes = dataset_settings[args.dataset]['num_classes']
input_size = dataset_settings[args.dataset]['input_size']
label = dataset_settings[args.dataset]['label']
print("Evaluating total class number {} with {}".format(
num_classes, label))
model = networks.init_model('resnet101',
num_classes=num_classes,
pretrained=None)
state_dict = torch.load(args.model_restore)['state_dict']
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in state_dict.items():
name = k[7:] # remove `module.`
new_state_dict[name] = v
model.load_state_dict(new_state_dict)
model.cuda()
model.eval()
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
dataset = SimpleFolderDataset(root=args.input_dir,
input_size=input_size,
transform=transform)
dataloader = DataLoader(dataset)
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
palette = get_palette(num_classes)
with torch.no_grad():
for idx, batch in enumerate(tqdm(dataloader)):
image, meta = batch
img_name = meta['name'][0]
c = meta['center'].numpy()[0]
s = meta['scale'].numpy()[0]
w = meta['width'].numpy()[0]
h = meta['height'].numpy()[0]
output = model(image.cuda())
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(output[0][-1][0].unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2, 0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
parsing_result_path = os.path.join(args.output_dir,
img_name[:-4] + '.png')
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
output_img.putpalette(palette)
output_img.save(parsing_result_path)
if args.logits:
logits_result_path = os.path.join(args.output_dir,
img_name[:-4] + '.npy')
np.save(logits_result_path, logits_result)
return
def Process_image(self):
if ((os.path.isfile(images_folder_path + '/front.png')) &
(os.path.isfile(images_folder_path + '/side.png'))):
input_size = [512, 512]
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
dataset = SimpleFolderDataset(root=images_folder_path,
input_size=input_size,
transform=transform)
dataloader = DataLoader(dataset)
palette = get_palette(num_classes)
with torch.no_grad():
for idx, batch in enumerate(tqdm(dataloader)):
image, meta = batch
img_name = meta['name'][0]
c = meta['center'].numpy()[0]
s = meta['scale'].numpy()[0]
w = meta['width'].numpy()[0]
h = meta['height'].numpy()[0]
output = model(image.cuda())
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(output[0][-1][0].unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2,
0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
parsing_result_path = os.path.join(output_path,
img_name[:-4] + '.png')
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
output_img.putpalette(palette)
output_img.save(parsing_result_path)
self.process_button = False
actual_height = (12 * self.height_feet + self.height_inch
) * 2.54 # in cm, (1 inch = 2.54 cm)
f_path = images_folder_path + '/front.png'
human_part_seg_f_path = output_path + '/front.png'
i1 = cv2.imread(f_path)
m1 = cv2.imread(human_part_seg_f_path)
s_path = images_folder_path + '/side.png'
human_part_seg_s_path = output_path + '/side.png'
i2 = cv2.imread(s_path)
m2 = cv2.imread(human_part_seg_s_path)
actual_height = (12 * self.height_feet +
self.height_inch) * 2.54 # conversion in cm
get_measuremnets(i1, m1, i2, m2, actual_height, True)
else:
if self.img_timer_flag == False:
self.current_img_timer = time.time()
self.img_timer_flag = True
count_down = self.image_timer_value - np.int(
time.time() - self.current_img_timer)
if (self.img_timer_flag and count_down <= self.image_timer_value):
self.current_frame = write_data(self.current_frame,
'Please save some images', 0.0,
0.4, 1.0, 0.15, 0.18, 0.10, 1,
2, (255, 255, 255))
if count_down == 0 or self.button_selected(self.return_point):
self.process_button = False
self.img_timer_flag = False
def main():
args = get_arguments()
# gpus = [int(i) for i in args.gpu.split(',')]
# assert len(gpus) == 1
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
num_classes = dataset_settings[args.dataset]['num_classes']
input_size = dataset_settings[args.dataset]['input_size']
label = dataset_settings[args.dataset]['label']
print("Evaluating total class number {} with {}".format(
num_classes, label))
model = networks.init_model('resnet101',
num_classes=num_classes,
pretrained=None)
state_dict = torch.load(args.model_restore) #['state_dict']
from collections import OrderedDict
new_state_dict = OrderedDict()
secretary = change_dict.dictModify(new_dict=new_state_dict,
old_dict=state_dict)
new_state_dict = secretary.arange()
# for k, v in state_dict.items():
# name = k[7:] # remove `module.`
# new_state_dict[name] = v
model.load_state_dict(new_state_dict)
# print(model)
# # model.cuda()
# model = torch.load("log/entire_model.pth", map_location=torch.device('cpu'))
model.eval()
input = torch.randn(1, 3, 473, 473)
ONNX_FILE_PATH = "pretrain_model/local.onnx"
ONNX_SIM_FILE_PATH = "pretrain_model/sim_local.onnx"
# torch.onnx.export(model, input, ONNX_FILE_PATH, input_names=['input'], output_names=['output'], opset_version=11) #, operator_export_type=torch.onnx.OperatorExportTypes.ONNX_ATEN_FALLBACK)
# onnx_model = onnx.load(ONNX_FILE_PATH)
# sim_model, check = onnxsim.simplify(onnx_model)
# onnx.save(sim_model, ONNX_SIM_FILE_PATH)
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
transformer = SimpleVideo(transforms=transform, input_size=[473, 473])
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
color_man = gray2color.makeColor(num_classes)
VIDEO_PATH = "input.mp4"
cap = cv2.VideoCapture(VIDEO_PATH)
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
out = cv2.VideoWriter('outpy.avi',
cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 24,
(frame_width, frame_height))
with torch.no_grad():
start = time.time()
count = 0
ret = True
while (cap.isOpened()):
ret, frame = cap.read()
if ret == True:
frame, meta = transformer.get_item(frame)
c = meta['center']
s = meta['scale']
w = meta['width']
h = meta['height']
# out_put = model(frame)
output = model(frame)
# output = model(image.cuda())
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(output[0][-1][0].unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2,
0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
out_img = np.array(output_img)
output_img = color_man.G2C(out_img)
out.write(np.array(output_img))
cv2.imshow("Tanned", np.array(output_img))
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if args.logits:
logits_result_path = os.path.join(args.output_dir,
img_name[:-4] + '.npy')
np.save(logits_result_path, logits_result)
count += 1
else:
break
end = time.time()
cap.release()
out.release()
print(
"Processed {} images using {:.5} seconds, average each image took {:.5} seconds"
.format(count, end - start, (end - start) / (count + 0.1)))
return
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
multi_scales = [float(i) for i in args.multi_scales.split(',')]
gpus = [int(i) for i in args.gpu.split(',')]
assert len(gpus) == 1
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
cudnn.benchmark = True
cudnn.enabled = True
h, w = map(int, args.input_size.split(','))
input_size = [h, w]
model = networks.init_model(args.arch,
num_classes=args.num_classes,
pretrained=None)
IMAGE_MEAN = model.mean
IMAGE_STD = model.std
INPUT_SPACE = model.input_space
print('image mean: {}'.format(IMAGE_MEAN))
print('image std: {}'.format(IMAGE_STD))
print('input space:{}'.format(INPUT_SPACE))
if INPUT_SPACE == 'BGR':
print('BGR Transformation')
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=IMAGE_MEAN, std=IMAGE_STD),
])
if INPUT_SPACE == 'RGB':
print('RGB Transformation')
transform = transforms.Compose([
transforms.ToTensor(),
BGR2RGB_transform(),
transforms.Normalize(mean=IMAGE_MEAN, std=IMAGE_STD),
])
# Data loader
lip_test_dataset = CropDataValSet(args.data_dir,
args.split_name,
crop_size=input_size,
transform=transform,
flip=args.flip)
num_samples = len(lip_test_dataset)
print('Totoal testing sample numbers: {}'.format(num_samples))
testloader = data.DataLoader(lip_test_dataset,
batch_size=args.batch_size,
shuffle=False,
pin_memory=True)
# Load model weight
state_dict = torch.load(args.model_restore)
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in state_dict.items():
name = k[7:] # remove `module.`
new_state_dict[name] = v
model.load_state_dict(new_state_dict)
model.cuda()
model.eval()
sp_results_dir = os.path.join(args.log_dir, args.split_name + '_parsing')
if not os.path.exists(sp_results_dir):
os.makedirs(sp_results_dir)
palette = get_palette(20)
parsing_preds = []
scales = np.zeros((num_samples, 2), dtype=np.float32)
centers = np.zeros((num_samples, 2), dtype=np.int32)
with torch.no_grad():
for idx, batch in enumerate(tqdm(testloader)):
image, meta = batch
if (len(image.shape) > 4):
image = image.squeeze()
im_name = meta['name'][0]
c = meta['center'].numpy()[0]
s = meta['scale'].numpy()[0]
w = meta['width'].numpy()[0]
h = meta['height'].numpy()[0]
scales[idx, :] = s
centers[idx, :] = c
parsing, logits = multi_scale_testing(model,
image.cuda(),
crop_size=input_size,
flip=args.flip,
multi_scales=multi_scales)
if args.save_results:
parsing_result = transform_parsing(parsing, c, s, w, h,
input_size)
parsing_result_path = os.path.join(sp_results_dir,
im_name + '.png')
output_im = PILImage.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
output_im.putpalette(palette)
output_im.save(parsing_result_path)
# save logits
logits_result = transform_logits(logits, c, s, w, h,
input_size)
logits_result_path = os.path.join(sp_results_dir,
im_name + '.npy')
np.save(logits_result_path, logits_result)
return
def main():
args = get_arguments()
# gpus = [int(i) for i in args.gpu.split(',')]
# assert len(gpus) == 1
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
num_classes = dataset_settings[args.dataset]['num_classes']
input_size = dataset_settings[args.dataset]['input_size']
label = dataset_settings[args.dataset]['label']
# Model in torch init
model = networks.init_model('resnet101',
num_classes=num_classes,
pretrained=None)
state_dict = torch.load(args.model_restore) #['state_dict']
from collections import OrderedDict
new_state_dict = OrderedDict()
secretary = change_dict.dictModify(new_dict=new_state_dict,
old_dict=state_dict)
new_state_dict = secretary.arange()
model.load_state_dict(new_state_dict)
model.eval()
print("Evaluating total class number {} with {}".format(
num_classes, label))
sess = onnxruntime.InferenceSession("pretrain_model/sim_local.onnx")
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
transformer = SimpleVideo(transforms=transform, input_size=[473, 473])
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
color_man = gray2color.makeColor(num_classes)
VIDEO_PATH = "input.mp4"
cap = cv2.VideoCapture(VIDEO_PATH)
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
out = cv2.VideoWriter('outpy.avi',
cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 24,
(frame_width * 3, frame_height))
with torch.no_grad():
start = time.time()
count = 0
ret = True
while (cap.isOpened()):
ret, frame = cap.read()
if ret == True:
# w, h, _ = frame.shape
# c, s, w, h = cal_chwsr(0, 0, w, h)
# frame = torch.tensor(frame)
print("frame: {}".format(frame.shape))
frame, meta = transformer.get_item(frame)
c = meta['center']
s = meta['scale']
w = meta['width']
h = meta['height']
# out_put = model(frame)
# input_name = sess.get_inputs()[0].name
# print("input name:", input_name)
# input_shape = sess.get_inputs()[0].shape
# print("input shape:", input_shape)
# input_type = sess.get_inputs()[0].type
# print("input type:", input_type)
input_name = sess.get_inputs()[0].name
# output_name = sess.get_outputs()[0].name
output_name = list(['output', '1250', '1245'])
pre_output = sess.run(
output_name,
input_feed={sess.get_inputs()[0].name: np.array(frame)})
output = [[pre_output[0], pre_output[1]], [pre_output[2]]]
output_t = model(frame)
# Post-process for output from onnx model
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(
torch.tensor(output[0][-1][0]).unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2,
0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
out_img_o = np.array(output_img)
output_img_o = color_man.G2C(out_img_o)
# Post-process for torch model
upsample_output = upsample(
torch.tensor(output_t[0][-1][0]).unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2,
0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
out_t_min = np.array(output_img)
out_img_t = np.array(output_img)
output_img_t = color_man.G2C(out_img_t)
# final = cv2.hconcat(output_img_t, out_img_t-out_img_o)
final = cv2.hconcat([
output_img_t,
cv2.cvtColor(out_img_t - out_img_o, cv2.COLOR_GRAY2RGB) *
100, output_img_o
])
out.write(np.array(final))
cv2.imshow("Tanned", np.array(final))
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if args.logits:
logits_result_path = os.path.join(args.output_dir,
img_name[:-4] + '.npy')
np.save(logits_result_path, logits_result)
count += 1
else:
break
end = time.time()
cap.release()
out.release()
print(
"Processed {} images using {:.5} seconds, average each image took {:.5} seconds"
.format(count, end - start, (end - start) / (count + 0.1)))
return
def main():
args = get_arguments()
gpus = [int(i) for i in args.gpu.split(',')]
assert len(gpus) == 1
if not args.gpu == 'None':
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
num_classes = dataset_settings[args.dataset]['num_classes']
input_size = dataset_settings[args.dataset]['input_size']
label = dataset_settings[args.dataset]['label']
print("Evaluating total class number {} with {}".format(
num_classes, label))
model = networks.init_model('resnet101',
num_classes=num_classes,
pretrained=None)
state_dict = torch.load(args.model_restore)['state_dict']
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in state_dict.items():
name = k[7:] # remove `module.`
new_state_dict[name] = v
model.load_state_dict(new_state_dict)
model.cuda()
model.eval()
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
dataset = SimpleFolderDataset(root=args.input_dir,
input_size=input_size,
transform=transform)
dataloader = DataLoader(dataset)
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
palette = get_palette(num_classes)
with torch.no_grad():
for idx, batch in enumerate(tqdm(dataloader)):
image, meta = batch
img_name = meta['name'][0]
img_path = meta['img_path'][0]
c = meta['center'].numpy()[0]
s = meta['scale'].numpy()[0]
w = meta['width'].numpy()[0]
h = meta['height'].numpy()[0]
output = model(image.cuda())
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(output[0][-1][0].unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2, 0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
output_img.putpalette(palette)
png_path = os.path.join(args.output_dir, img_name[:-4] + '.png')
output_img.save(png_path)
# 'lip': {
# 'input_size': [473, 473],
# 'num_classes': 20,
# 'label': ['Background', 'Hat', 'Hair', 'Glove', 'Sunglasses', 'Upper-clothes', 'Dress', 'Coat',
# 'Socks', 'Pants', 'Jumpsuits', 'Scarf', 'Skirt', 'Face', 'Left-arm', 'Right-arm',
# 'Left-leg', 'Right-leg', 'Left-shoe', 'Right-shoe']
# },
parsing_result = (parsing_result >= 5) & (parsing_result != 13)
parsing_result = parsing_result.astype(int)
parsing_result = parsing_result * 255
org_img = Image.open(img_path)
f = Image.fromarray(np.asarray(parsing_result, dtype=np.uint8))
org_img.putalpha(f)
org_img = np.array(org_img)
# https://stackoverflow.com/a/55973647/1513627
# Alpha -> Green
org_img[org_img[..., -1] == 0] = [0, 255, 0, 0]
jpg_path = os.path.join(args.output_dir, img_name[:-4] + '.jpg')
Image.fromarray(org_img).convert('RGB').save(jpg_path)
if args.logits:
logits_result_path = os.path.join(args.output_dir,
img_name[:-4] + '.npy')
np.save(logits_result_path, logits_result)
return
def process_image(feet, inch):
if (os.path.isfile(os.getcwd() + image_saved_path + '/front.png')
and os.path.isfile(os.getcwd() + image_saved_path + '/side.png')):
input_size = [512, 512]
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.406, 0.456, 0.485],
std=[0.225, 0.224, 0.229])
])
dataset = SimpleFolderDataset(root=os.getcwd() + image_saved_path,
input_size=input_size,
transform=transform)
dataloader = DataLoader(dataset)
palette = get_palette(num_classes)
with torch.no_grad():
for idx, batch in enumerate(tqdm(dataloader)):
image, meta = batch
img_name = meta['name'][0]
c = meta['center'].numpy()[0]
s = meta['scale'].numpy()[0]
w = meta['width'].numpy()[0]
h = meta['height'].numpy()[0]
output = model(image.cuda())
upsample = torch.nn.Upsample(size=input_size,
mode='bilinear',
align_corners=True)
upsample_output = upsample(output[0][-1][0].unsqueeze(0))
upsample_output = upsample_output.squeeze()
upsample_output = upsample_output.permute(1, 2,
0) # CHW -> HWC
logits_result = transform_logits(
upsample_output.data.cpu().numpy(),
c,
s,
w,
h,
input_size=input_size)
parsing_result = np.argmax(logits_result, axis=2)
parsing_result_path = os.path.join(
os.getcwd() + process_image_path, img_name[:-4] + '.png')
output_img = Image.fromarray(
np.asarray(parsing_result, dtype=np.uint8))
output_img.putpalette(palette)
output_img.save(parsing_result_path)
actual_height = (12 * feet + inch) * 2.54 # in cm
i1_path = os.getcwd() + image_saved_path + '/front.png'
i1 = cv2.imread(i1_path)
m1_path = os.getcwd() + process_image_path + '/front.png'
m1 = cv2.imread(m1_path)
i2_path = os.getcwd() + image_saved_path + '/side.png'
i2 = cv2.imread(i2_path)
m2_path = os.getcwd() + process_image_path + '/side.png'
m2 = cv2.imread(m2_path)
status, waist, chest, thigh, front_sleeve_in_cm, dis_in_cm, image, side_image = get_measuremnets(
i1, m1, i2, m2, actual_height, True)
return status, waist, chest, thigh, front_sleeve_in_cm, dis_in_cm, image, side_image
else:
return False, -1, -1, -1, -1, -1, None, None
