def transform(self, img, hflip=False): if self.crop is not None: if isinstance(self.crop, int): img = tfs.CenterCrop(self.crop)(img) else: assert len(self.crop) == 4, 'Crop size must be an integer for center crop, or a list of 4 integers (y0,x0,h,w)' img = tfs.crop(img, *self.crop) img = tfs.resize(img, (self.image_size, self.image_size)) if hflip: img = tfs.hflip(img) return tfs.to_tensor(img)
def get_latent(self, input_image): input_image = (input_image - 127.5) / 127.5 input_image = np.expand_dims(input_image, axis=2) input_image = input_image.transpose(2, 0, 1) input_image = np.expand_dims(input_image, axis=0) input_image = input_image.astype('float32') input_image = transform.to_tensor(jt.array(input_image)) mus_mouth = self.net_encoder(input_image) print('mus_mouth:', mus_mouth.shape) return mus_mouth
def __getitem__(self, index): img, target = self.data[index], self.targets[index] # doing this so that it is consistent with all other datasets # to return a PIL Image img = Image.fromarray(img) if self.transform is not None: img = self.transform(img) if self.target_transform is not None: target = self.target_transform(target) return trans.to_tensor(img), target
def verify_img_data(img_data, expected_output, mode): if mode is None: img = transform.ToPILImage()(img_data) self.assertEqual(img.mode, 'RGB') # default should assume RGB else: img = transform.ToPILImage(mode=mode)(img_data) self.assertEqual(img.mode, mode) split = img.split() for i in range(3): self.assertTrue( np.allclose(expected_output[:, :, i], transform.to_tensor(split[i])))
def __getitem__(self, index): A_path = self.file_paths[index] A = Image.open(A_path) new_w = 512 new_h = 512 A = A.resize((new_w, new_h), Image.NEAREST) A_tensor = transform.to_tensor(A) * 255.0 if self.part_sketch != 'bg': loc_p = self.part[self.part_sketch] A_tensor = A_tensor[0, loc_p[1]:loc_p[1] + loc_p[2], loc_p[0]:loc_p[0] + loc_p[2]] else: for key_p in self.part.keys(): if key_p != 'bg': loc_p = self.part[key_p] A_tensor[0, loc_p[1]:loc_p[1] + loc_p[2], loc_p[0]:loc_p[0] + loc_p[2]] = 255 A_tensor = (A_tensor - 127.5) / 127.5 A_tensor = np.expand_dims(A_tensor, axis=0) A_tensor = A_tensor.astype('float32') A_tensor = transform.to_tensor(jt.array(A_tensor)) return A_tensor
def __getitem__(self, index): img = Image.fromarray(self.mnist['images'][index]).convert('RGB') if self.transform: img = self.transform(img) return trans.to_tensor(img), self.mnist['labels'][index]
def __call__(self, image, target): image = T.to_tensor(image) return image, target
def __call__(self, image, target): return T.to_tensor(image), target
def __call__(self, img): from jittor.transform import to_tensor return to_tensor(img)