Python torchvision.transforms.ToPILImage() Examples
The following are 30
code examples of torchvision.transforms.ToPILImage().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
torchvision.transforms
, or try the search function
.
![](https://www.programcreek.com/common/static/images/search.png)
Example #1
Source File: mask_generators.py From vaeac with MIT License | 7 votes |
def regenerate_cache(self): """ Resamples the big matrix and resets the counter of the total number of elements in the returned masks. """ low_size = int(self.resolution * self.max_size) low_pattern = self.rng.uniform(0, 1, size=(low_size, low_size)) * 255 low_pattern = torch.from_numpy(low_pattern.astype('float32')) pattern = transforms.Compose([ transforms.ToPILImage(), transforms.Resize(self.max_size, Image.BICUBIC), transforms.ToTensor(), ])(low_pattern[None])[0] pattern = torch.lt(pattern, self.density).byte() self.pattern = pattern.byte() self.points_used = 0
Example #2
Source File: datasets.py From multiple-objects-gan with MIT License | 6 votes |
def get_imgs(img_path, imsize, bbox=None, transform=None, normalize=None): img = Image.open(img_path).convert('RGB') if transform is not None: img = transform(img) img, bbox_scaled = crop_imgs(img, bbox) ret = [] if cfg.GAN.B_DCGAN: ret = [normalize(img)] else: for i in range(cfg.TREE.BRANCH_NUM): # print(imsize[i]) if i < (cfg.TREE.BRANCH_NUM - 1): re_img = transforms.ToPILImage()(img) re_img = transforms.Resize((imsize[i], imsize[i]))(re_img) else: re_img = transforms.ToPILImage()(img) ret.append(normalize(re_img)) return ret, bbox_scaled
Example #3
Source File: datasets.py From semantic-object-accuracy-for-generative-text-to-image-synthesis with MIT License | 6 votes |
def get_imgs(img_path, imsize, max_objects, bbox=None, transform=None, normalize=None): img = Image.open(img_path).convert('RGB') if transform is not None: img = transform(img) img, bbox_scaled = crop_imgs(img, bbox, max_objects=max_objects) ret = [] if cfg.GAN.B_DCGAN: ret = [normalize(img)] else: for i in range(cfg.TREE.BRANCH_NUM): # print(imsize[i]) if i < (cfg.TREE.BRANCH_NUM - 1): re_img = transforms.ToPILImage()(img) re_img = transforms.Resize((imsize[i], imsize[i]))(re_img) else: re_img = transforms.ToPILImage()(img) ret.append(normalize(re_img)) return ret, bbox_scaled
Example #4
Source File: train.py From pytorch-zssr with Apache License 2.0 | 6 votes |
def test(model, img, sr_factor): model.eval() img = img.resize((int(img.size[0]*sr_factor), \ int(img.size[1]*sr_factor)), resample=PIL.Image.BICUBIC) img.save('low_res.png') img = transforms.ToTensor()(img) img = torch.unsqueeze(img, 0) input = Variable(img.cuda()) residual = model(input) output = input + residual output = output.cpu().data[0, :, :, :] o = output.numpy() o[np.where(o < 0)] = 0.0 o[np.where(o > 1)] = 1.0 output = torch.from_numpy(o) output = transforms.ToPILImage()(output) output.save('zssr.png')
Example #5
Source File: super.py From jdit with Apache License 2.0 | 6 votes |
def image(self, img_tensors: torch.Tensor, global_step: int, tag: str = "Train/input", grid_size: Union[list, tuple] = (3, 1), shuffle=True, save_file=False): if len(img_tensors.size()) != 4: raise TypeError("img_tensors rank should be 4, got %d instead" % len(img_tensors.size())) self._build_dir(os.path.join(self.logdir, "plots", tag)) rows, columns = grid_size[0], grid_size[1] batch_size = len(img_tensors) # img_tensors =>(batchsize, 3, 256, 256) num_samples: int = min(batch_size, rows * columns) sampled_tensor = self._sample(img_tensors, num_samples, shuffle).detach().cpu() # (sample_num, 3, 32,32) tensors # sampled_images = map(transforms.Normalize(mean, std), sampled_tensor) # (sample_num, 3, 32,32) images sampled_images: torch.Tensor = make_grid(sampled_tensor, nrow=rows, normalize=True, scale_each=True) self.writer.add_image(tag, sampled_images, global_step) if save_file: img = transforms.ToPILImage()(sampled_images) filename = "%s/plots/%s/E%03d.png" % (self.logdir, tag, global_step) img.save(filename)
Example #6
Source File: dataset.py From PerceptualGAN with GNU General Public License v3.0 | 6 votes |
def __getitem__(self, index): outputs = [] for i, d in enumerate(self.datasets): outputs += d.get_item(self.indices[i][index], self.flips[i][index]) self.counter += 1 # Shuffle datasets after each epoch if self.counter == len(self): if self.phase == 'train': self.shuffle() self.counter = 0 if len(outputs) == 1 and self.aligned: # Super resolution outputs[0] = ToPILImage()((outputs[0] + 1) / 2) outputs.insert(0, self.down(outputs[0])) for i, o in enumerate(outputs): outputs[i] = ToTensor()(o) * 2 - 1 return outputs
Example #7
Source File: dataset.py From kaggle_carvana_segmentation with MIT License | 6 votes |
def im_show(img_list): """ It receives a list of images and plots them together :param img_list: :return: """ to_PIL = transforms.ToPILImage() if len(img_list) >= 10: raise Exception("len(img_list) must be smaller than 10") for idx, img in enumerate(img_list): img = np.array(to_PIL(img)) plt.subplot(100 + 10 * len(img_list) + (idx + 1)) fig = plt.imshow(img) fig.axes.get_xaxis().set_visible(False) fig.axes.get_yaxis().set_visible(False) plt.show()
Example #8
Source File: file_dataset_test.py From baal with Apache License 2.0 | 6 votes |
def test_segmentation_pipeline(self): class DrawSquare: def __init__(self, side): self.side = side def __call__(self, x, **kwargs): x, canvas = x # x is a [int, ndarray] canvas[:self.side, :self.side] = x return canvas target_trans = BaaLCompose( [GetCanvas(), DrawSquare(3), ToPILImage(mode=None), Resize(60, interpolation=0), RandomRotation(10, resample=NEAREST, fill=0.0), PILToLongTensor()]) file_dataset = FileDataset(self.paths, [1] * len(self.paths), self.transform, target_trans) x, y = file_dataset[0] assert np.allclose(np.unique(y), [0, 1]) assert y.shape[1:] == x.shape[1:]
Example #9
Source File: trainer.py From tiny-faces-pytorch with MIT License | 6 votes |
def visualize_output(img, output, templates, proc, prob_thresh=0.55, nms_thresh=0.1): tensor_to_image = transforms.ToPILImage() mean = [0.485, 0.456, 0.406] std = [0.229, 0.224, 0.225] for t, m, s in zip(img[0], mean, std): t.mul_(s).add_(m) image = tensor_to_image(img[0]) # Index into the batch cls_map = nnfunc.sigmoid(output[:, 0:templates.shape[0], :, :]).data.cpu( ).numpy().transpose((0, 2, 3, 1))[0, :, :, :] reg_map = output[:, templates.shape[0]:, :, :].data.cpu( ).numpy().transpose((0, 2, 3, 1))[0, :, :, :] print(np.sort(np.unique(cls_map))[::-1]) proc.visualize_heatmaps(image, cls_map, reg_map, templates, prob_thresh=prob_thresh, nms_thresh=nms_thresh) p = input("Continue? [Yn]") if p.lower().strip() == 'n': exit(0)
Example #10
Source File: cifar10.py From SE_DenseNet with MIT License | 6 votes |
def get_dataloader(batch_size, root="data/cifar10"): root = Path(root).expanduser() if not root.exists(): root.mkdir() root = str(root) to_normalized_tensor = [transforms.ToTensor(), transforms.ToPILImage(), transforms.Resize((224, 224)), transforms.ToTensor(), transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))] data_augmentation = [transforms.RandomHorizontalFlip(),] train_loader = DataLoader( datasets.CIFAR10(root, train=True, download=True, transform=transforms.Compose(data_augmentation + to_normalized_tensor)), batch_size=batch_size, shuffle=True) test_loader = DataLoader( datasets.CIFAR10(root, train=False, transform=transforms.Compose(to_normalized_tensor)), batch_size=batch_size, shuffle=True) return train_loader, test_loader
Example #11
Source File: trainer.py From pggan-pytorch with MIT License | 6 votes |
def feed_interpolated_input(self, x): if self.phase == 'gtrns' and floor(self.resl)>2 and floor(self.resl)<=self.max_resl: alpha = self.complete['gen']/100.0 transform = transforms.Compose( [ transforms.ToPILImage(), transforms.Scale(size=int(pow(2,floor(self.resl)-1)), interpolation=0), # 0: nearest transforms.Scale(size=int(pow(2,floor(self.resl))), interpolation=0), # 0: nearest transforms.ToTensor(), ] ) x_low = x.clone().add(1).mul(0.5) for i in range(x_low.size(0)): x_low[i] = transform(x_low[i]).mul(2).add(-1) x = torch.add(x.mul(alpha), x_low.mul(1-alpha)) # interpolated_x if self.use_cuda: return x.cuda() else: return x
Example #12
Source File: LiveCamera.py From simple-HRNet with GNU General Public License v3.0 | 5 votes |
def __init__(self, camera_id=0, epoch_length=1, resolution=(384, 288), interpolation=cv2.INTER_CUBIC, multiperson=False, device=torch.device('cpu')): super(LiveCameraDataset, self).__init__() self.camera_id = camera_id self.epoch_length = epoch_length self.resolution = resolution self.interpolation = interpolation self.multiperson = multiperson self.device = device self.camera = cv2.VideoCapture(self.camera_id) assert self.camera.isOpened() if not self.multiperson: self.transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), ]) else: self.detector = YOLOv3(model_def="./models/detectors/yolo/config/yolov3.cfg", class_path="./models/detectors/yolo/data/coco.names", weights_path="./models/detectors/yolo/weights/yolov3.weights", classes=('person',), device=device) self.transform = transforms.Compose([ transforms.ToPILImage(), transforms.Resize((self.resolution[1], self.resolution[0])), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), ])
Example #13
Source File: predict.py From Pytorch-UNet with GNU General Public License v3.0 | 5 votes |
def predict_img(net, full_img, device, scale_factor=1, out_threshold=0.5): net.eval() img = torch.from_numpy(BasicDataset.preprocess(full_img, scale_factor)) img = img.unsqueeze(0) img = img.to(device=device, dtype=torch.float32) with torch.no_grad(): output = net(img) if net.n_classes > 1: probs = F.softmax(output, dim=1) else: probs = torch.sigmoid(output) probs = probs.squeeze(0) tf = transforms.Compose( [ transforms.ToPILImage(), transforms.Resize(full_img.size[1]), transforms.ToTensor() ] ) probs = tf(probs.cpu()) full_mask = probs.squeeze().cpu().numpy() return full_mask > out_threshold
Example #14
Source File: trainer.py From PAST-ReID with MIT License | 5 votes |
def __init__(self, args, cls_params=None, tblogger=None): super(ReIDTrainer, self).__init__() self.args = args self.cls_params = cls_params self.tblogger = tblogger self.init_log() self.init_device() if not self.args.evaluate: self.init_trainer() self.init_eval() self.to_pil_image = transforms.ToPILImage()
Example #15
Source File: DD.py From DEEPSEC with MIT License | 5 votes |
def __getitem__(self, index): single_image, single_label = self.images[index], self.labels[index] if self.transform: img = ToPILImage(mode=self.color_mode)(single_image) single_image = self.transform(img) return single_image, single_label
Example #16
Source File: predictor.py From FreeAnchor with MIT License | 5 votes |
def build_transform(self): """ Creates a basic transformation that was used to train the models """ cfg = self.cfg # we are loading images with OpenCV, so we don't need to convert them # to BGR, they are already! So all we need to do is to normalize # by 255 if we want to convert to BGR255 format, or flip the channels # if we want it to be in RGB in [0-1] range. if cfg.INPUT.TO_BGR255: to_bgr_transform = T.Lambda(lambda x: x * 255) else: to_bgr_transform = T.Lambda(lambda x: x[[2, 1, 0]]) normalize_transform = T.Normalize( mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD ) transform = T.Compose( [ T.ToPILImage(), T.Resize(self.min_image_size), T.ToTensor(), to_bgr_transform, normalize_transform, ] ) return transform
Example #17
Source File: utils.py From SRN-DeblurNet with MIT License | 5 votes |
def resize(x, size): transform = transforms.Compose([ transforms.ToPILImage(), transforms.Scale(size), transforms.ToTensor(), ]) return transform(x)
Example #18
Source File: vis_tools.py From Lighthead-RCNN-in-Pytorch0.4.1 with MIT License | 5 votes |
def show_util_with_conf(conf,idx,imgs, labels_group, bboxes_group, confidences_group, cls_conf_group, correct_id_2_class, class_2_color): if torch.sum(torch.abs(bboxes_group[idx])).item() == 0: return trans.ToPILImage()(de_preprocess(conf, imgs[idx].cpu())) return draw_bbox_class_with_conf(conf, trans.ToPILImage()(de_preprocess(conf, imgs[idx].cpu())),\ labels_group[idx].cpu(), bboxes_group[idx].cpu(),\ correct_id_2_class, class_2_color, \ confidences_group[idx].cpu(), cls_conf_group[idx].cpu())
Example #19
Source File: InputTransformations.py From DEEPSEC with MIT License | 5 votes |
def defend_jpeg(input_tensor, image_mode, quality): pil_image = ToPILImage(mode=image_mode)(input_tensor) fd = BytesIO() pil_image.save(fd, format='jpeg', quality=quality) # quality level specified in paper jpeg_image = ToTensor()(PIL.Image.open(fd)) return jpeg_image # based on https://github.com/scikit-image/scikit-image/blob/master/skimage/restoration/_denoise_cy.pyx # super slow since this is implemented in pure python :'(
Example #20
Source File: EIT.py From DEEPSEC with MIT License | 5 votes |
def __getitem__(self, index): single_image, single_label = self.images[index], self.labels[index] if self.transform: img = ToPILImage(mode=self.color_mode)(single_image) single_image = self.transform(img) return single_image, single_label
Example #21
Source File: EIT.py From DEEPSEC with MIT License | 5 votes |
def image_crop_rescale(sample, crop_size, color_mode): image = ToPILImage(mode=color_mode)(sample) cropped_image = RandomCrop(crop_size)(image) rescaled_image = Resize((sample.shape[1], sample.shape[2]), interpolation=0)(cropped_image) cropped_rescaled_sample = ToTensor()(rescaled_image) return cropped_rescaled_sample
Example #22
Source File: test_recipes.py From Torchelie with MIT License | 5 votes |
def test_deepdream(): model = nn.Sequential(nn.Conv2d(3, 6, 3)) dd = DeepDream(model, '0') dd.fit(ToPILImage()(torch.randn(3, 128, 128)), 1)
Example #23
Source File: utils.py From Deep-Expander-Networks with GNU General Public License v3.0 | 5 votes |
def __call__(self, img): centerCrop = transforms.CenterCrop(self.size) toPILImage = transforms.ToPILImage() toTensor = transforms.ToTensor() if self.opt.dataset == 'tuberlin': normalize = transforms.Normalize(mean=[0.06,], std=[0.93]) if self.opt.dataset == 'sketchyrecognition': normalize = transforms.Normalize(mean=[0.0465,], std=[0.9]) w, h = img.size(2), img.size(1) temp_output = [] output = torch.FloatTensor(10, img.size(0), self.size, self.size) img = toPILImage(img) for img_cur in [img, img.transpose(Image.FLIP_LEFT_RIGHT)]: temp_output.append(centerCrop(img_cur)) temp_output.append(img_cur.crop([0, 0, self.size, self.size])) temp_output.append(img_cur.crop([w-self.size, 0, w, self.size])) temp_output.append(img_cur.crop([0, h-self.size, self.size, h])) temp_output.append(img_cur.crop([w-self.size, h-self.size, w, h])) for img_idx in range(10): img_cur = temp_output[img_idx] img_cur = toTensor(img_cur) img_cur = normalize(img_cur) output[img_idx] = img_cur.view(img_cur.size(0), img_cur.size(1), img_cur.size(2)) return output
Example #24
Source File: trainer.py From pytorch_segmentation with MIT License | 5 votes |
def __init__(self, model, loss, resume, config, train_loader, val_loader=None, train_logger=None, prefetch=True): super(Trainer, self).__init__(model, loss, resume, config, train_loader, val_loader, train_logger) self.wrt_mode, self.wrt_step = 'train_', 0 self.log_step = config['trainer'].get('log_per_iter', int(np.sqrt(self.train_loader.batch_size))) if config['trainer']['log_per_iter']: self.log_step = int(self.log_step / self.train_loader.batch_size) + 1 self.num_classes = self.train_loader.dataset.num_classes # TRANSORMS FOR VISUALIZATION self.restore_transform = transforms.Compose([ local_transforms.DeNormalize(self.train_loader.MEAN, self.train_loader.STD), transforms.ToPILImage()]) self.viz_transform = transforms.Compose([ transforms.Resize((400, 400)), transforms.ToTensor()]) if self.device == torch.device('cpu'): prefetch = False if prefetch: self.train_loader = DataPrefetcher(train_loader, device=self.device) self.val_loader = DataPrefetcher(val_loader, device=self.device) torch.backends.cudnn.benchmark = True
Example #25
Source File: img_loader.py From torch-light with MIT License | 5 votes |
def tensor2img(self, tensor, epoch): decode = transforms.Compose([transforms.Lambda(lambda x: x.mul_(1./255)), transforms.Normalize(mean=[-0.40760392, -0.45795686, -0.48501961], std=[1,1,1]), transforms.Lambda(lambda x: x[torch.LongTensor([2,1,0])]), ]) tensor = decode(tensor) loader = transforms.Compose([transforms.ToPILImage()]) img = loader(tensor.clamp_(0, 1)) img.save(self.img_path + "/result_{}.jpg".format(epoch))
Example #26
Source File: img_loader.py From torch-light with MIT License | 5 votes |
def imshow(tensor, imsize=512, title=None): image = tensor.clone().cpu() image = image.view(*tensor.size()) image = transforms.ToPILImage()(image) plt.imshow(image) if title is not None: plt.title(title) plt.pause(5)
Example #27
Source File: utils.py From tvnet_pytorch with MIT License | 5 votes |
def save_im_tensor(x, addr): x = x.cpu().float() transpose = transforms.ToPILImage() x = transpose(x[0]) x.save(addr)
Example #28
Source File: utils.py From tvnet_pytorch with MIT License | 5 votes |
def im_tensor_to_numpy(x): transpose = transforms.ToPILImage() x = np.asarray(transpose(x)) return x
Example #29
Source File: test_recipes.py From Torchelie with MIT License | 5 votes |
def test_neuralstyle(): stylizer = NeuralStyle() content = ToPILImage()(torch.randn(3, 64, 64)) style_img = ToPILImage()(torch.randn(3, 64, 64)) result = stylizer.fit(1, content, style_img, 1, ['conv1_1'])
Example #30
Source File: test_tranforms.py From Torchelie with MIT License | 5 votes |
def test_resizedcrop(): img = ToPILImage()(torch.clamp(torch.randn(3, 30, 16) + 1, min=0, max=1)) tf = ResizedCrop(48) tf(img)