.ipynb_checkpoints/headpose_video.py-checkpoint.ipynb
File was deleted .ipynb_checkpoints/load_300W_LP-checkpoint.ipynb
File was deleted code/batch_testing.py
File was deleted code/batch_testing_preangles.py
File was deleted code/datasets.py
@@ -164,88 +164,6 @@ # 122,450 return self.length class Pose_300W_LP_SR(Dataset): def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat', image_mode='RGB'): self.data_dir = data_dir self.transform = transform self.img_ext = img_ext self.annot_ext = annot_ext filename_list = get_list_from_filenames(filename_path) self.X_train = filename_list self.y_train = filename_list self.image_mode = image_mode self.length = len(filename_list) def __getitem__(self, index): img = Image.open(os.path.join(self.data_dir, self.X_train[index] + self.img_ext)) img = img.convert(self.image_mode) mat_path = os.path.join(self.data_dir, self.y_train[index] + self.annot_ext) # Crop the face pt2d = utils.get_pt2d_from_mat(mat_path) x_min = min(pt2d[0,:]) y_min = min(pt2d[1,:]) x_max = max(pt2d[0,:]) y_max = max(pt2d[1,:]) # k = 0.2 to 0.40 k = np.random.random_sample() * 0.2 + 0.2 x_min -= 0.6 * k * abs(x_max - x_min) y_min -= 2 * k * abs(y_max - y_min) x_max += 0.6 * k * abs(x_max - x_min) y_max += 0.6 * k * abs(y_max - y_min) img = img.crop((int(x_min), int(y_min), int(x_max), int(y_max))) # We get the pose in radians pose = utils.get_ypr_from_mat(mat_path) # And convert to degrees. pitch = pose[0] * 180 / np.pi yaw = pose[1] * 180 / np.pi roll = pose[2] * 180 / np.pi rnd = np.random.random_sample() if rnd < 0.5: ds = 10 original_size = img.size img = img.resize((img.size[0] / ds, img.size[1] / ds), resample=Image.NEAREST) img = img.resize((original_size[0], original_size[1]), resample=Image.NEAREST) # Flip? rnd = np.random.random_sample() if rnd < 0.5: yaw = -yaw roll = -roll img = img.transpose(Image.FLIP_LEFT_RIGHT) # Blur? rnd = np.random.random_sample() if rnd < 0.05: img = img.filter(ImageFilter.BLUR) img_ycc = img.convert('YCbCr') # Bin values bins = np.array(range(-99, 102, 3)) binned_pose = np.digitize([yaw, pitch, roll], bins) - 1 labels = torch.LongTensor(np.concatenate((binned_pose, shape), axis = 0)) cont_labels = torch.FloatTensor([yaw, pitch, roll]) # Transforms img = transforms.Scale(240)(img) img = transforms.RandomCrop(224)(img) img_ycc = img.convert('YCbCr') img = transforms.ToTensor() img_ycc = transforms.ToTensor() return img, img_ycc, labels, cont_labels, self.X_train[index] def __len__(self): # 122,450 return self.length class AFLW2000(Dataset): def __init__(self, data_dir, filename_path, transform, img_ext='.jpg', annot_ext='.mat', image_mode='RGB'): self.data_dir = data_dir @@ -395,21 +313,6 @@ yaw = -yaw roll = -roll img = img.transpose(Image.FLIP_LEFT_RIGHT) # Blur? # rnd = np.random.random_sample() # if rnd < 0.05: # img = img.filter(ImageFilter.BLUR) # if rnd < 0.025: # img = img.filter(ImageFilter.BLUR) # # rnd = np.random.random_sample() # if rnd < 0.05: # nb = np.random.randint(1,5) # img = img.rotate(-nb) # elif rnd > 0.95: # nb = np.random.randint(1,5) # img = img.rotate(nb) # Bin values bins = np.array(range(-99, 102, 3)) code/hopenet.py
@@ -4,41 +4,6 @@ import math import torch.nn.functional as F # CNN Model (2 conv layer) class Simple_CNN(nn.Module): def __init__(self): super(Simple_CNN, self).__init__() self.layer1 = nn.Sequential( nn.Conv2d(3, 64, kernel_size=3, padding=0), nn.BatchNorm2d(64), nn.ReLU(), nn.MaxPool2d(2)) self.layer2 = nn.Sequential( nn.Conv2d(64, 128, kernel_size=3, padding=0), nn.BatchNorm2d(128), nn.ReLU(), nn.MaxPool2d(2)) self.layer3 = nn.Sequential( nn.Conv2d(128, 256, kernel_size=3, padding=0), nn.BatchNorm2d(256), nn.ReLU(), nn.MaxPool2d(2)) self.layer4 = nn.Sequential( nn.Conv2d(256, 512, kernel_size=3, padding=0), nn.BatchNorm2d(512), nn.ReLU(), nn.MaxPool2d(2)) self.fc = nn.Linear(17*17*512, 3) def forward(self, x): out = self.layer1(x) out = self.layer2(out) out = self.layer3(out) out = self.layer4(out) out = out.view(out.size(0), -1) out = self.fc(out) return out class Hopenet(nn.Module): # This is just Hopenet with 3 output layers for yaw, pitch and roll. def __init__(self, block, layers, num_bins, iter_ref): @@ -224,93 +189,3 @@ pitch = self.fc_pitch(x) roll = self.fc_roll(x) return yaw, pitch, roll class Hopenet_new(nn.Module): # This is just Hopenet with 3 output layers for yaw, pitch and roll. def __init__(self, block, layers, num_bins): self.inplanes = 64 super(Hopenet_new, self).__init__() self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(64) self.relu = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AvgPool2d(7) self.fc_yaw = nn.Linear(512 * block.expansion, num_bins) self.fc_pitch = nn.Linear(512 * block.expansion, num_bins) self.fc_roll = nn.Linear(512 * block.expansion, num_bins) self.softmax = nn.Softmax() self.fc_finetune_new = nn.Linear(512 * block.expansion + 256 * block.expansion + 3, 3) self.conv1x1 = nn.Conv2d(1024, 64, kernel_size = 1, stride = 1, bias=False) self.maxpool_interm = nn.MaxPool2d(kernel_size=5, stride=3, padding=1) self.idx_tensor = Variable(torch.FloatTensor(range(66))).cuda() for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) return nn.Sequential(*layers) def forward(self, x): x = self.conv1(x) x = self.bn1(x) x = self.relu(x) x = self.maxpool(x) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x_interm = self.conv1x1(x) x_interm = self.relu(x_interm) x_interm = self.maxpool_interm(x_interm) x_interm = x_interm.view(x_interm.size(0), -1) x = self.layer4(x) x = self.avgpool(x) x = x.view(x.size(0), -1) pre_yaw = self.fc_yaw(x) pre_pitch = self.fc_pitch(x) pre_roll = self.fc_roll(x) yaw = self.softmax(pre_yaw) yaw = Variable(torch.sum(yaw.data * self.idx_tensor.data, 1), requires_grad=True) * 3 - 99 pitch = self.softmax(pre_pitch) pitch = Variable(torch.sum(pitch.data * self.idx_tensor.data, 1), requires_grad=True) * 3 - 99 roll = self.softmax(pre_roll) roll = Variable(torch.sum(roll.data * self.idx_tensor.data, 1), requires_grad=True) * 3 - 99 yaw = yaw.view(yaw.size(0), 1) pitch = pitch.view(pitch.size(0), 1) roll = roll.view(roll.size(0), 1) preangles = torch.cat([yaw, pitch, roll], 1) # angles predicts the residual residuals = self.fc_finetune_new(torch.cat((preangles, x_interm, x), 1)) final_angles = preangles + residuals return pre_yaw, pre_pitch, pre_roll, preangles, final_angles code/pretrain_SRNet.py
code/test.py
File was deleted code/test_new.py
File was deleted code/test_preangles_extreme.py
File was deleted code/test_resnet50_regression_extreme.py
File was deleted code/train.py
File was deleted code/train_hopenet_new.py
File was deleted code/train_hopenet_sr.py
File was deleted code/train_preangles_focalloss.py
File was deleted practice/.ipynb_checkpoints/AFLW2000-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/BIWI-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/create_filtered_datasets-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/load_300W-LP-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/load_AFLW-Copy1-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/load_AFLW-KEPLER_split-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/load_AFLW-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/output_viz-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/remove_AFLW2000-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/remove_KEPLER_test_split-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/shape_space-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/smoothing_ypr-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/vis_AFLW-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/vis_AFW-checkpoint.ipynb
File was deleted practice/.ipynb_checkpoints/vis_LS3D-checkpoint.ipynb
File was deleted practice/AFLW2000.ipynb
File was deleted practice/BIWI.ipynb
File was deleted practice/create_filtered_datasets.ipynb
File was deleted practice/headpose_video.py.ipynb
File was deleted practice/load_300W-LP.ipynb
File was deleted practice/load_AFLW-Copy1.ipynb
File was deleted practice/load_AFLW-KEPLER_split.ipynb
File was deleted practice/load_AFLW.ipynb
File was deleted practice/output_viz.ipynb
File was deleted practice/remove_AFLW2000.ipynb
File was deleted practice/remove_KEPLER_test_split.ipynb
File was deleted practice/shape_space.ipynb
File was deleted practice/smoothing_ypr.ipynb
File was deleted practice/untitled.txt
practice/vis_AFLW.ipynb
File was deleted practice/vis_AFW.ipynb
File was deleted practice/vis_LS3D.ipynb
File was deleted
