def build_model(self):
""" DataLoader """
pad = int(30 * self.img_size // 256)
train_transform = T.Compose([
T.RandomHorizontalFlip(),
T.Resize((self.img_size + pad, self.img_size + pad)),
T.RandomCrop(self.img_size),
T.ToTensor(),
T.Normalize(mean=0.5, std=0.5),
])
test_transform = T.Compose([
T.Resize((self.img_size, self.img_size)),
T.ToTensor(),
T.Normalize(mean=0.5, std=0.5)
])
self.trainA = ImageFolder('dataset/photo2cartoon/trainA', self.img_size, train_transform)
self.trainB = ImageFolder('dataset/photo2cartoon/trainB', self.img_size, train_transform)
self.testA = ImageFolder('dataset/photo2cartoon/testA', self.img_size, test_transform)
self.testB = ImageFolder('dataset/photo2cartoon/testB', self.img_size, test_transform)
self.trainA_loader = DataLoader(self.trainA, batch_size=self.batch_size, shuffle=True)
self.trainB_loader = DataLoader(self.trainB, batch_size=self.batch_size, shuffle=True)
self.testA_loader = DataLoader(self.testA, batch_size=1, shuffle=False)
self.testB_loader = DataLoader(self.testB, batch_size=1, shuffle=False)
""" Define Generator, Discriminator """
self.genA2B = ResnetGenerator(ngf=self.ch, img_size=self.img_size, light=self.light)
self.genB2A = ResnetGenerator(ngf=self.ch, img_size=self.img_size, light=self.light)
self.disGA = Discriminator(input_nc=3, ndf=self.ch, n_layers=7)
self.disGB = Discriminator(input_nc=3, ndf=self.ch, n_layers=7)
self.disLA = Discriminator(input_nc=3, ndf=self.ch, n_layers=5)
self.disLB = Discriminator(input_nc=3, ndf=self.ch, n_layers=5)
""" Define Loss """
self.L1_loss = nn.loss.L1Loss()
self.MSE_loss = nn.loss.MSELoss()
self.BCE_loss = nn.loss.BCEWithLogitsLoss()
self.G_optim = paddle.optimizer.Adam(
learning_rate=self.lr, beta1=0.5, beta2=0.999, weight_decay=0.0001,
parameters=self.genA2B.parameters()+self.genB2A.parameters()
)
self.D_optim = paddle.optimizer.Adam(
learning_rate=self.lr, beta1=0.5, beta2=0.999, weight_decay=0.0001,
parameters=self.disGA.parameters()+self.disGB.parameters()+self.disLA.parameters()+self.disLB.parameters()
)
self.Rho_clipper = RhoClipper(0, self.rho_clipper)
self.W_clipper = WClipper(0, self.w_clipper)
def test_to_tensor(self):
trans = transforms.Compose([transforms.ToTensor()])
fake_img = self.create_image((50, 100, 3))
tensor = trans(fake_img)
assert isinstance(tensor, paddle.Tensor)
np.testing.assert_equal(tensor.shape, (3, 50, 100))
def test_det(
opt,
batch_size=12,
img_size=(1088, 608),
iou_thres=0.5,
print_interval=40,
):
data_cfg = opt.data_cfg
f = open(data_cfg)
data_cfg_dict = json.load(f)
f.close()
nC = 1
test_path = data_cfg_dict['test']
dataset_root = data_cfg_dict['root']
if opt.gpus[0] >= 0:
# opt.device = torch.device('cuda')
opt.device = 'gpu'
else:
# opt.device = torch.device('cpu')
opt.device = 'cpu'
paddle.set_device(opt.device)
print('Creating model...')
model = create_model(opt.arch, opt.heads, opt.head_conv)
model = load_model(model, opt.load_model)
#model = torch.nn.DataParallel(model)
# model = model.to(opt.device)
model.eval()
# Get dataloader
transforms = T.Compose([T.ToTensor()])
dataset = DetDataset(dataset_root, test_path, img_size, augment=False, transforms=transforms)
dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=False,
num_workers=8, drop_last=False, collate_fn=collate_fn)
mean_mAP, mean_R, mean_P, seen = 0.0, 0.0, 0.0, 0
print('%11s' * 5 % ('Image', 'Total', 'P', 'R', 'mAP'))
outputs, mAPs, mR, mP, TP, confidence, pred_class, target_class, jdict = \
[], [], [], [], [], [], [], [], []
AP_accum, AP_accum_count = np.zeros(nC), np.zeros(nC)
for batch_i, (imgs, targets, paths, shapes, targets_len) in enumerate(dataloader):
t = time.time()
#seen += batch_size
output = model(imgs.cuda())[-1]
origin_shape = shapes[0]
width = origin_shape[1]
height = origin_shape[0]
inp_height = img_size[1]
inp_width = img_size[0]
c = np.array([width / 2., height / 2.], dtype=np.float32)
s = max(float(inp_width) / float(inp_height) * height, width) * 1.0
meta = {'c': c, 's': s,
'out_height': inp_height // opt.down_ratio,
'out_width': inp_width // opt.down_ratio}
hm = output['hm'].sigmoid_()
wh = output['wh']
reg = output['reg'] if opt.reg_offset else None
opt.K = 200
detections, inds = mot_decode(hm, wh, reg=reg, ltrb=opt.ltrb, K=opt.K)
# Compute average precision for each sample
targets = [targets[i][:int(l)] for i, l in enumerate(targets_len)]
for si, labels in enumerate(targets):
seen += 1
#path = paths[si]
#img0 = cv2.imread(path)
dets = detections[si]
dets = dets.unsqueeze(0)
dets = post_process(opt, dets, meta)
dets = merge_outputs(opt, [dets])[1]
#remain_inds = dets[:, 4] > opt.det_thres
#dets = dets[remain_inds]
if dets is None:
# If there are labels but no detections mark as zero AP
if labels.size(0) != 0:
mAPs.append(0), mR.append(0), mP.append(0)
continue
# If no labels add number of detections as incorrect
correct = []
if labels.size(0) == 0:
# correct.extend([0 for _ in range(len(detections))])
mAPs.append(0), mR.append(0), mP.append(0)
continue
else:
target_cls = labels[:, 0]
# Extract target boxes as (x1, y1, x2, y2)
target_boxes = xywh2xyxy(labels[:, 2:6])
target_boxes[:, 0] *= width
target_boxes[:, 2] *= width
target_boxes[:, 1] *= height
target_boxes[:, 3] *= height
'''
path = paths[si]
img0 = cv2.imread(path)
img1 = cv2.imread(path)
for t in range(len(target_boxes)):
x1 = target_boxes[t, 0]
y1 = target_boxes[t, 1]
x2 = target_boxes[t, 2]
y2 = target_boxes[t, 3]
cv2.rectangle(img0, (x1, y1), (x2, y2), (0, 255, 0), 4)
cv2.imwrite('gt.jpg', img0)
for t in range(len(dets)):
x1 = dets[t, 0]
y1 = dets[t, 1]
x2 = dets[t, 2]
y2 = dets[t, 3]
cv2.rectangle(img1, (x1, y1), (x2, y2), (0, 255, 0), 4)
cv2.imwrite('pred.jpg', img1)
abc = ace
'''
detected = []
for *pred_bbox, conf in dets:
obj_pred = 0
pred_bbox = torch.FloatTensor(pred_bbox).view(1, -1)
# Compute iou with target boxes
iou = bbox_iou(pred_bbox, target_boxes, x1y1x2y2=True)[0]
# Extract index of largest overlap
best_i = np.argmax(iou)
# If overlap exceeds threshold and classification is correct mark as correct
if iou[best_i] > iou_thres and obj_pred == labels[best_i, 0] and best_i not in detected:
correct.append(1)
detected.append(best_i)
else:
correct.append(0)
# Compute Average Precision (AP) per class
AP, AP_class, R, P = ap_per_class(tp=correct,
conf=dets[:, 4],
pred_cls=np.zeros_like(dets[:, 4]), # detections[:, 6]
target_cls=target_cls)
# Accumulate AP per class
AP_accum_count += np.bincount(AP_class, minlength=nC)
AP_accum += np.bincount(AP_class, minlength=nC, weights=AP)
# Compute mean AP across all classes in this image, and append to image list
mAPs.append(AP.mean())
mR.append(R.mean())
mP.append(P.mean())
# Means of all images
mean_mAP = np.sum(mAPs) / (AP_accum_count + 1E-16)
mean_R = np.sum(mR) / (AP_accum_count + 1E-16)
mean_P = np.sum(mP) / (AP_accum_count + 1E-16)
if batch_i % print_interval == 0:
# Print image mAP and running mean mAP
print(('%11s%11s' + '%11.3g' * 4 + 's') %
(seen, dataloader.dataset.nF, mean_P, mean_R, mean_mAP, time.time() - t))
# Print mAP per class
print('%11s' * 5 % ('Image', 'Total', 'P', 'R', 'mAP'))
print('AP: %-.4f\n\n' % (AP_accum[0] / (AP_accum_count[0] + 1E-16)))
# Return mAP
return mean_mAP, mean_R, mean_P
def __len__(self):
return len(self.img_names)
if __name__ == '__main__':
from paddle.vision.transforms import transforms as T
from paddle.io import DataLoader
img_size = 256
pad = 30
train_transform = T.Compose([
T.RandomHorizontalFlip(),
T.Resize((img_size + pad, img_size + pad)),
T.RandomCrop(img_size),
T.ToTensor(),
T.Normalize(mean=0.5, std=0.5)
])
dataloader = ImageFolder('dataset/photo2cartoon/trainB',
transform=train_transform)
train_loader = DataLoader(dataloader, batch_size=1, shuffle=True)
print('num: ', len(train_loader))
for i in range(300):
print(i)
try:
real_A, _ = next(trainA_iter)
except:
trainA_iter = iter(train_loader())
real_A, _ = next(trainA_iter)
def do_transform(self, trans):
trans.transforms.insert(0, transforms.ToTensor(data_format='CHW'))
trans.transforms.append(transforms.Transpose(order=(1, 2, 0)))
dataset_folder = DatasetFolder(self.data_dir, transform=trans)
for _ in dataset_folder:
pass
Created on : 2021/5/18 21:15 @author: Jeremy """ ''' 增加了paddle.Model高层API，大部分任务可以使用此API用于简化训练、评估、预测类代码开发。 注意区别Model和Net概念，Net是指继承paddle.nn.Layer的网络结构； 而Model是指持有一个Net对象，同时指定损失函数、优化算法、评估指标的可训练、评估、预测的实例。 ''' import paddle from paddle.vision.transforms import transforms from paddle.io import DataLoader # transform = transforms.Compose([transforms.ToTensor()]) # # train_data = paddle.vision.datasets.MNIST(mode='train',transform = transform) # test_data = paddle.vision.datasets.MNIST(mode='test',transform= transform) # lenet = paddle.vision.models.LeNet() # # # Mnist继承paddle.nn.Layer属于Net，model包含了训练功能 # # model = paddle.Model(lenet) # # 设置训练模型所需的optimizer, loss, metric # model.prepare( # paddle.optimizer.Adam(learning_rate=0.001,parameters=model.parameters()), # paddle.nn.CrossEntropyLoss(), # paddle.metric.Accuracy() # ) #