def main(): # --------- 1. get image path and name --------- model_name = 'u2net_portrait' #u2netp image_dir = './test_data/test_portrait_images/portrait_im' prediction_dir = './test_data/test_portrait_images/portrait_results' if (not os.path.exists(prediction_dir)): os.mkdir(prediction_dir) model_dir = './saved_models/u2net_portrait/u2net_portrait.pth' img_name_list = glob.glob(image_dir + '/*') print("Number of images: ", len(img_name_list)) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(512), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- print("...load U2NET---173.6 MB") net = U2NET(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = 1.0 - d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def preprocess(image): #print('Start image preprocess') label_3 = np.zeros(image.shape) label = np.zeros(label_3.shape[0:2]) if (3 == len(label_3.shape)): label = label_3[:, :, 0] elif (2 == len(label_3.shape)): label = label_3 if (3 == len(image.shape) and 2 == len(label.shape)): label = label[:, :, np.newaxis] elif (2 == len(image.shape) and 2 == len(label.shape)): image = image[:, :, np.newaxis] label = label[:, :, np.newaxis] transform = transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) sample = transform({ 'imidx': np.array([0]), 'image': image, 'label': label }) #print('Preprocess completed') return sample
def __init__(self, model_name='u2net', cuda_mode=True, output_format='np'): self.model_name = model_name self.cuda_mode = cuda_mode and torch.cuda.is_available() # Fallback to CPU mode, if cuda is not available self.trans = transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) self.output_format = output_format # Validate if output_format not in self.FORMATS: raise AssertionError('Invalid "output_format"', 'Use "np" or "pil"') if model_name not in self.MODEL_NAMES: raise AssertionError('Invalid "model_name"', 'Use "u2net" or "u2netp"') if model_name == 'u2net': print("Model: U2NET (173.6 MB)") self.net = U2NET(3, 1) # 173.6 MB elif model_name == 'u2netp': print("Model: U2NetP (4.7 MB)") self.net = U2NETP(3, 1) # 4.7 MB else: raise AssertionError('Invalid "model_name"', 'Use "u2net" or "u2netp"') # Load network model_file = os.path.join(os.path.dirname(__file__), 'saved_models', model_name + '.pth') print("model_file:", model_file) if cuda_mode: print("CUDA mode") self.net.load_state_dict(torch.load(model_file)) self.net.cuda() else: print("CPU mode") self.net.load_state_dict(torch.load(model_file, map_location=torch.device('cpu'))) self.net.eval()
def main(): # --------- 1. get image path and name --------- model_name = 'u2net' #u2netp image_dir = './save_images/images/' prediction_dir = './save_images/' + model_name + '_result/' model_dir = './saved_models/' + model_name + '/' + model_name + '.pth' img_name_list = glob.glob(image_dir + '*') print(img_name_list) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split("/")[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def run(orig_image): torch.cuda.empty_cache() image = np.array(orig_image) # Preprocess image label_3 = np.zeros(image.shape) label = np.zeros(label_3.shape[0:2]) if (3 == len(label_3.shape)): label = label_3[:, :, 0] elif (2 == len(label_3.shape)): label = label_3 if (3 == len(image.shape) and 2 == len(label.shape)): label = label[:, :, np.newaxis] elif (2 == len(image.shape) and 2 == len(label.shape)): image = image[:, :, np.newaxis] label = label[:, :, np.newaxis] transform = transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) sample = transform({ 'imidx': np.array([0]), 'image': image, 'label': label }) # Process image image_process = sample['image'].unsqueeze(0) image_process = image_process.type(torch.FloatTensor) if torch.cuda.is_available(): image_process = Variable(image_process.cuda()) else: image_process = Variable(image_process) d1, d2, d3, d4, d5, d6, d7 = net(image_process) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save mask predict = pred predict = predict.squeeze() predict_np = predict.cpu().data.numpy() im = Image.fromarray(predict_np * 255).convert('RGB').convert('L') imo = im.resize((image.shape[1], image.shape[0]), resample=Image.BILINEAR) pb_np = np.array(imo) del d1, d2, d3, d4, d5, d6, d7 return imo
def process_image(self, image): """ :param image: image of type numpy array :return: processed image """ transformer = transforms.Compose([RescaleT(256), ToTensorLab(flag=0)]) image = transformer(image) image = image.unsqueeze(0) image = image.type(torch.FloatTensor) image = Variable(image) return image
def main(): image_dir = '/media/markytools/New Volume/Courses/EE298CompVis/finalproject/datasets/DUTS/DUTS-TE/DUTS-TE-Image/' prediction_dir = './predictionout/' model_dir = './saved_models/basnet_bsi_dataaugandarchi/basnet_bsi_epoch_207_itr_272000_train_9.345837_tar_1.082428.pth' img_name_list = glob.glob(image_dir + '*.jpg') # --------- 2. dataloader --------- #1. dataload test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(256), ToTensorLab(flag=0)]), category="test") test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- print("...load BASNet...") net = BASNet(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split("/")[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) # d1,d2,d3,d4,d5,d6,d7,d8 = net(inputs_test) d1, d2, d3, d4, d5, d6, d7, d8, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct = net( inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7, d8
def main(colored=False, imagepath=''): # --------- 1. get image path and name --------- model_name='u2net'#u2netp prediction_dir = './test_data/' + model_name + '_results/' model_dir = './saved_models/'+ model_name + '/' + model_name + '.pth' # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset(img_name_list = [imagepath], lbl_name_list = [], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) ) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- if(model_name=='u2net'): print("...load U2NET---173.6 MB") net = U2NET(3,1) elif(model_name=='u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3,1) net.load_state_dict(torch.load(model_dir, map_location=torch.device('cpu'))) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for _, data_test in enumerate(test_salobj_dataloader): inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1,d2,d3,d4,d5,d6,d7= net(inputs_test) # normalization pred = d1[:,0,:,:] pred = normPRED(pred) del d1,d2,d3,d4,d5,d6,d7 # save results to test_results folder return save_output(imagepath, pred, prediction_dir, colored=colored)
def main(): # --------- 1. get image path and name --------- model_name = 'u2net' cwd = Path(os.getcwd()) image_dir = cwd / 'test_data' / 'test_human_images' prediction_dir = cwd / 'test_data' / 'test_human_images_results' prediction_dir.mkdir(exist_ok=True) model_dir = cwd / 'saved_models' / (model_name + '_human_seg') / (model_name + '_human_seg.pth') img_name_list = list(image_dir.glob('*')) print("Images in test:", len(img_name_list)) # --------- 2. dataloader --------- # 1. dataloader test_salobj_dataset = SalObjDataset(img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) ) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- print("...load U2NET---173.6 MB") net = U2NET(3, 1) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') net.load_state_dict(torch.load(model_dir, map_location=device)).to(device) net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): image_path = img_name_list[i_test] print("inferencing:", image_path.name) inputs_test = data_test['image'] inputs_test = inputs_test.to(next(net.parameters())) with torch.no_grad(): d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder save_output(image_path, pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def infer( net, image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images'), prediction_dir = os.path.join(os.getcwd(), 'test_data', 'u2net' + '_results') ): img_name_list = glob.glob(image_dir + os.sep + '*') prediction_dir = prediction_dir + os.sep # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset(img_name_list = img_name_list, lbl_name_list = [], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) ) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("Generating mask for:",img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1,d2,d3,d4,d5,d6,d7= net(inputs_test) # normalization pred = d1[:,0,:,:] pred = normPRED(pred) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_images(img_name_list[i_test],pred,prediction_dir) del d1,d2,d3,d4,d5,d6,d7
def main(): # --------- 1. get image path and name --------- model_name = 'u2netp' # u2netp image_dir = '../train2014' prediction_dir = os.path.join(os.getcwd(), 'test_data', model_name + '_results' + os.sep) model_dir = '../models/' + model_name + '.pth' img_name_list = glob.glob(image_dir + os.sep + '*') # --------- 2. dataloader --------- # 1. dataloader test_salobj_dataset = SalObjDataset(img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) ) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) net.load_state_dict(torch.load(model_dir)) # if torch.cuda.is_available(): # net.cuda() net.eval() all_out = {} for i_test, data_test in tqdm(enumerate(test_salobj_dataloader)): sep_ = img_name_list[i_test].split(os.sep)[-1] inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) # # if torch.cuda.is_available(): # inputs_test = Variable(inputs_test.cuda()) # else: inputs_test = Variable(inputs_test) d = net(inputs_test) pred = normPRED(d) all_out[sep_] = pred pickle.dump(all_out, open("../data/coco_train_u2net.pik", "wb"), protocol=2)
def run_prediction(files): img_name_list = files # --------- 2. dataloader --------- #1. dataload test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(256), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- print("...load BASNet...") net = BASNet(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split("/")[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1, d2, d3, d4, d5, d6, d7, d8 = net(inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7, d8
def main(): # --------- 1. get image path and name --------- model_name = 'u2net_portrait' #u2netp image_dir = './test_data/test_portrait_images/portrait_im' prediction_dir = './test_data/test_portrait_images/portrait_results' if(not os.path.exists(prediction_dir)): os.mkdir(prediction_dir) model_dir = './saved_models/u2net_portrait/u2net_portrait.pth' img_name_list = glob.glob(image_dir+'/*') print("Number of images: ", len(img_name_list)) # --------- 2. dataloader --------- test_salobj_dataset = sal_generator(batch_size=1, img_name_list = img_name_list, lbl_name_list = [], transform=transforms.Compose([RescaleT(512), ToTensorLab(flag=0)]) ) # --------- 3. model define --------- print("...load U2NET---173.6 MB") net = U2NET(3,1) net.load(model_dir) # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataset): print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) d1,d2,d3,d4,d5,d6,d7= net(data_test, steps=1) # normalization pred = 1.0 - d1[:,0,:,:] pred = normPRED(pred) # save results to test_results folder save_output(img_name_list[i_test],pred,prediction_dir) del d1,d2,d3,d4,d5,d6,d7
def remove_bg(images): dataset = SalObjDataset(img_name_list=images, lbl_name_list=[], transform=transforms.Compose( [RescaleT(320), ToTensorLab(flag=0)])) dataloader = DataLoader(dataset, batch_size=1, shuffle=False, num_workers=1) net = U2NET(3, 1) net.load_state_dict(torch.load(model_dir, map_location='cpu')) net.eval() outputs = [] for i, data in enumerate(dataloader): inputs = data['image'] inputs = inputs.type(torch.FloatTensor) inputs = Variable(inputs) d1, d2, d3, d4, d5, d6, d7 = net(inputs) pred = d1[:, 0, :, :] pred = normPRED(pred) filename = save_output(images[i], pred, output_dir) outputs.append(filename) img = cv2.imread(images[i]) mask = cv2.imread(filename, 0) rgba = cv2.cvtColor(img, cv2.COLOR_RGB2RGBA) rgba[:, :, 3] = mask cv2.imwrite(filename, rgba) del d1, d2, d3, d4, d5, d6, d7 return outputs
def preprocess(image): label_3 = np.zeros(image.shape) label = np.zeros(label_3.shape[0:2]) if (3 == len(label_3.shape)): label = label_3[:, :, 0] elif (2 == len(label_3.shape)): label = label_3 if (3 == len(image.shape) and 2 == len(label.shape)): label = label[:, :, np.newaxis] elif (2 == len(image.shape) and 2 == len(label.shape)): image = image[:, :, np.newaxis] label = label[:, :, np.newaxis] transform = transforms.Compose([RescaleT(256), ToTensorLab(flag=0)]) sample = transform({'image': image, 'label': label}) return sample
def main(): model_name='u2netp' model_dir = os.path.join(os.getcwd(), 'saved_models', model_name, model_name + '.pth') image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images') img_name_list = glob.glob(image_dir + os.sep + '*') test_salobj_dataset = SalObjDataset(img_name_list = img_name_list, lbl_name_list = [], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) ) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) if(model_name=='u2net'): print("...load U2NET---173.6 MB") net = U2NET(3,1) elif(model_name=='u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3,1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() for data_test in test_salobj_dataloader: inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) dummy_input = inputs_test torch.onnx.export(net, dummy_input,"exported/onnx/{}.onnx".format(model_name), opset_version=10) break
def get_foreground(img): global model_loaded, net if not model_loaded: basnet_model_file = downloads.download_from_gdrive( gdrive_fileid='1s52ek_4YTDRt_EOkx1FS53u-vJa0c4nu', output_path='BASNet/saved_models/basnet_bsi/basnet.pth') net = load_model(basnet_model_file) model_loaded = True img = np.array(img) size = image.get_size(img) label = np.zeros(img.shape) sample = {'image': img, 'label': label} transform = transforms.Compose([RescaleT(256), ToTensorLab(flag=0)]) sample = transform(sample) inputs_test = sample['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) inputs_test = inputs_test.unsqueeze(0) d1, d2, d3, d4, d5, d6, d7, d8 = net(inputs_test) pred = d1[:, 0, :, :] pred = normPRED(pred) del d1, d2, d3, d4, d5, d6, d7, d8 pred = pred.squeeze() pred_np = pred.cpu().data.numpy() im_mask = Image.fromarray(pred_np * 255).convert('RGB') im_mask = im_mask.resize(size, resample=Image.BILINEAR) im_mask = np.array(im_mask) return im_mask
def main(): # --------- 1. get image path and name --------- model_name = 'u2net' # u2netp image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images') prediction_dir = os.path.join(os.getcwd(), 'test_data', model_name + '_results' + os.sep) model_dir = os.path.join(os.getcwd(), 'saved_models', model_name, model_name + '.pth') img_name_list = glob.glob(image_dir + os.sep + '*') print(img_name_list) # --------- 2. dataloader --------- test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) for i_test, data_test in enumerate(len(img_name_list)): print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) d1, d2, d3, d4, d5, d6, d7 = net.predict(test_salobj_dataset, steps=1) pred = d1[:, 0, :, :] pred = normPRED(pred) if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def main(): name = 'test' # please input the height unit:M body_height = 1.63 #"Input image" path image_dir = os.path.join(os.getcwd(), 'input') #"Output model" path outbody_filenames = './output/{}.obj'.format(name) ######################################################### #this code used for image segmentation to remove the background to get Silhouettes # --------- 1. get image path and name --------- model_name='u2net'#u2net or u2netp #set orignal silhouette images path prediction_dir1 = os.path.join(os.getcwd(), 'Silhouette' + os.sep) #set the path of silhouette images after horizontal flippath prediction_dir = os.path.join(os.getcwd(), 'test_data' + os.sep) model_dir = os.path.join(os.getcwd(), 'saved_models', model_name, model_name + '.pth') img_name_list = glob.glob(image_dir + os.sep + '*') print(img_name_list) # --------- 2. dataloader --------- test_salobj_dataset = SalObjDataset(img_name_list = img_name_list, lbl_name_list = [], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)]) ) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. silhouette cutting model define --------- if(model_name=='u2net'): print("...load U2NET---173.6 MB") net = U2NET(3,1) elif(model_name=='u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3,1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:",img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1,d2,d3,d4,d5,d6,d7= net(inputs_test) # normalization pred = d1[:,0,:,:] pred = normPRED(pred) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test],pred,prediction_dir,prediction_dir1) del d1,d2,d3,d4,d5,d6,d7 ########################################################### #this code used for reconstruct 3d model: #--------5.get the silhouette images -------- img_filenames = ['./test_data/front.png', './test_data/side.png'] # img = cv2.imread(img_filenames[1]) # cv2.flip(img,1) # -----------6.load input data--------- sampling_num = 648 data = np.zeros([2, 2, sampling_num]) for i in np.arange(len(img_filenames)): img = img_filenames[i] im = getBinaryimage(img, 600) # deal with white-black image simply sample_points = getSamplePoints(im, sampling_num, i) center_p = np.mean(sample_points, axis=0) sample_points = sample_points - center_p data[i, :, :] = sample_points.T data = repeat_data(data) #--------7 load CNN model----reconstruct 3d body shape print('==> begining...') len_out = 22 model_name = './Models/model.ckpt' ourModel = RegressionPCA(len_out) ourModel.load_state_dict(torch.load(model_name)) ourModel.eval() #----------8 output results-------------- save_obj(outbody_filenames, ourModel, body_height, data)
imidx = imidx + "." + bbb[i] tra_lbl_name_list.append(data_dir + tra_label_dir + imidx + label_ext) print("---") print("train images: ", len(tra_img_name_list)) print("train labels: ", len(tra_lbl_name_list)) print("---") train_num = len(tra_img_name_list) salobj_dataset = SalObjDataset( img_name_list=tra_img_name_list, lbl_name_list=tra_lbl_name_list, transform=transforms.Compose([ RescaleT(320), RandomCrop(288), ToTensorLab(flag=0)])) salobj_dataloader = DataLoader(salobj_dataset, batch_size=batch_size_train, shuffle=True #shuffle=False , num_workers=0) # ------- 3. define model -------- # define the net #选择模型 if(model_name=='u2net'): net = U2NET(3, 1) elif(model_name=='u2netp'): net = U2NETP(3,1) if torch.cuda.is_available():
imo.save(d_dir+imidx+'.png') # --------- 1. get image path and name --------- #image_dir = './test_data/test_images/' image_dir = '../SOD_datasets/DUTS-TE/img/' prediction_dir = './test_data/test_results/' model_dir = './saved_models/basnet_bsi_original/basnet_bsi_itr_574000_train_1.013724_tar_0.054404.pth' img_name_list = glob.glob(image_dir + '*.jpg') # --------- 2. dataloader --------- # 1. dataload test_salobj_dataset = SalObjDataset(img_name_list=img_name_list, lbl_name_list=[ ], transform=transforms.Compose([RescaleT(256), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader( test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- print("...load BASNet...") net = BASNet(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split("/")[-1])
def main(): # --------- 1. get image path and name --------- model_name = 'u2netp' # fixed as u2netp image_dir = os.path.join( os.getcwd(), 'input' ) # changed to 'images' directory which is populated while running the script prediction_dir = os.path.join( os.getcwd(), 'output/' ) # changed to 'results' directory which is populated after the predictions model_dir = os.path.join(os.getcwd(), model_name + '.pth') # path to u2netp pretrained weights img_name_list = glob.glob(image_dir + os.sep + '*') print(img_name_list) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- net = U2NETP(3, 1) if torch.cuda.is_available(): net.load_state_dict(torch.load(model_dir)) net.cuda() else: net.load_state_dict( torch.load(model_dir, map_location=torch.device('cpu'))) net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def main(): # --------- 1. get image path and name --------- #model_name='u2net' model_name = 'u2netp' image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images') prediction_dir = os.path.join(os.getcwd(), 'test_data', model_name + '_results' + os.sep) model_dir = os.path.join(os.getcwd(), 'saved_models', model_name, model_name + '.pth') img_name_list = glob.glob(image_dir + os.sep + '*') print(img_name_list) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] #print("test", inputs_test.shape) inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) #print("pred",pred.shape) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def main(): # --------- 1. get image path and name --------- model_name = 'u2net' #u2netp image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images') prediction_dir = os.path.join(os.getcwd(), 'test_data', model_name + '_results' + os.sep) # image_dir = os.path.join('/nfs/project/huxiaoliang/data/white_or_not/white_bg_image') # prediction_dir = os.path.join('/nfs/project/huxiaoliang/data/white_or_not/white_bg_image_pred'+ os.sep) model_dir = os.path.join('/nfs/private/modelfiles/u2net-saved_models', model_name, model_name + '.pth') img_name_list = glob.glob(image_dir + os.sep + '*') print(img_name_list) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- error = [] for i_test, data_test in enumerate(test_salobj_dataloader): try: print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1[:, 0, :, :] pred = normPRED(pred) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7 except Exception as ex: traceback.print_exc() error.append(img_name_list[i_test].split(os.sep)[-1]) print('异常数据:', error)
image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images') prediction_dir = os.path.join(os.getcwd(), 'test_data', model_name + '_results' + os.sep) model_dir = os.path.join(os.getcwd(), 'saved_models', model_name, model_name + '.pth') img_name_list = glob.glob(image_dir + os.sep + '*') print(img_name_list) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) criterion = torch.nn.CrossEntropyLoss() net.load_state_dict(torch.load(model_dir))
def main(): # --------- 1. get image path and name --------- model_name = 'u2net' #u2netp image_dir = "/home/vybt/Downloads/U2_Net_Test" prediction_dir = "/home/vybt/Downloads/u-2--bps-net-prediction" model_dir = '/media/vybt/DATA/SmartFashion/deep-learning-projects/U-2-Net/saved_models/u2net/_bps_bce_itr_300000_train_0.107041_tar_0.011690.pth' img_name_list = glob.glob(image_dir + os.sep + '*') # print(img_name_list) # --------- 2. dataloader --------- #1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([RescaleT(320), ToTensorLab(flag=0)])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=1) # --------- 3. model define --------- if model_name == 'u2net': print("...load U2NET---173.6 MB") net = U2NET(3, 8) elif model_name == 'u2netp': print("...load U2NEP---4.7 MB") net = U2NETP(3, 8) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("Inference: ", img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = Variable(inputs_test.cuda()) else: inputs_test = Variable(inputs_test) # print("inputs test: {}".format(inputs_test.shape)) d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1 pred = normPRED(pred) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def main(): # --------- 1. get image path and name --------- model_name = 'u2netp' # u2net # image_dir = os.path.join(os.getcwd(), 'test_data', 'test_images') image_dir = '/home/hha/dataset/circle/circle' prediction_dir = '/home/hha/dataset/circle/circle_pred' model_dir = '/home/hha/pytorch_code/U-2-Net-master/saved_models/u2netp/u2netp.pthu2netp_bce_itr_2000_train_0.077763_tar_0.006976.pth' # model_dir = os.path.join(os.getcwd(), 'saved_models', model_name, model_name + '.pth') img_name_list = glob.glob(image_dir + os.sep + '*') img_name_list = list(filter(lambda f: f.find('_mask') < 0, img_name_list)) # print(img_name_list) # --------- 2. dataloader --------- # 1. dataloader test_salobj_dataset = SalObjDataset( img_name_list=img_name_list, lbl_name_list=[], transform=transforms.Compose([ RescaleT(320), # 320 ToTensorLab(flag=0) ])) test_salobj_dataloader = DataLoader(test_salobj_dataset, batch_size=1, shuffle=False, num_workers=0) # --------- 3. model define --------- if (model_name == 'u2net'): print("...load U2NET---173.6 MB") net = U2NET(3, 1) elif (model_name == 'u2netp'): print("...load U2NEP---4.7 MB") net = U2NETP(3, 1) net.load_state_dict(torch.load(model_dir)) if torch.cuda.is_available(): net.cuda() net.eval() # --------- 4. inference for each image --------- for i_test, data_test in enumerate(test_salobj_dataloader): print("inferencing:", img_name_list[i_test].split(os.sep)[-1]) inputs_test = data_test['image'] inputs_test = inputs_test.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_test = inputs_test.cuda() else: inputs_test = inputs_test d1, d2, d3, d4, d5, d6, d7 = net(inputs_test) # normalization pred = d1[:, 0, :, :] # pred = normPRED(pred) # save results to test_results folder if not os.path.exists(prediction_dir): os.makedirs(prediction_dir, exist_ok=True) save_output(img_name_list[i_test], pred, prediction_dir) del d1, d2, d3, d4, d5, d6, d7
def predict(): # ensure an image was properly uploaded to our endpoint if flask.request.method == "POST": if flask.request.files.get("image"): file_image = flask.request.files["image"] #image = Image.open(image) # preprocess the image and prepare it for classification salobjdataset = SalObjDataset(img_name_list=[file_image], lbl_name_list=[], transform=transforms.Compose([ RescaleT(256), ToTensorLab(flag=0) ])) saldataloader = DataLoader(salobjdataset, batch_size=1, shuffle=False, num_workers=1) for image in saldataloader: input_image = image['image'] input_image = input_image.type(torch.FloatTensor) # classify the input image and then initialize the list # of predictions to return to the client #img = img.type(torch.FloatTensor) if torch.cuda.is_available(): input_image = Variable(input_image.cuda()) else: input_image = Variable(input_image) load_model() d1, d2, d3, d4, d5, d6, d7, d8 = net(input_image) pred = d1[:, 0, :, :] pred = normPRED(pred) predict = pred predict = predict.squeeze() predict_np = predict.cpu().data.numpy() im = Image.fromarray(predict_np * 255).convert('RGB') image = io.imread(file_image) imo = im.resize((image.shape[1], image.shape[0]), resample=Image.BILINEAR) pb_np = np.array(imo) in_img = cv2.imread(file_image) in_img = cv2.cvtColor(in_img, cv2.COLOR_BGR2RGB) result_img = cv2.imread(imo) result_img = cv2.cvtColor(result_img, cv2.COLOR_BGR2RGB) new_img = np.where(result_img < [250, 250, 250], [254, 254, 254], in_img) new_img = new_img.astype('uint8') new_img = cv2.cvtColor(new_img, cv2.COLOR_BGR2RGB) byte_io = io.BytesIO() new_img.save(byte_io, 'PNG') byte_io.seek(0) return flask.send_file(byte_io, mimetype='image/png')
def train(): data_dir = './train_data/' tra_image_dir = 'DUTS-TR/DUTS-TR-Image/' tra_label_dir = 'DUTS-TR/DUTS-TR-Mask/' image_ext = '.jpg' label_ext = '.png' model_dir = "./saved_models/basnet_bsi/" epoch_num = 100 batch_size_train = 1 batch_size_val = 1 train_num = 0 val_num = 0 tra_img_name_list = glob.glob(data_dir + tra_image_dir + '*' + image_ext) tra_lbl_name_list = glob.glob(data_dir + tra_label_dir + '*' + label_ext) # tra_lbl_name_list = [] # for img_path in tra_img_name_list: # img_name = img_path.split("/")[-1] # aaa = img_name.split(".") # print(aaa) # bbb = aaa[0:-1] # imidx = bbb[0] # for i in range(1,len(bbb)): # imidx = imidx + "." + bbb[i] # print(imidx) # tra_lbl_name_list.append(data_dir + tra_label_dir + '*' + label_ext) print("---") print("train images: ", len(tra_img_name_list)) print("train labels: ", len(tra_lbl_name_list)) print("---") train_num = len(tra_img_name_list) salobj_dataset = SalObjDataset(img_name_list=tra_img_name_list, lbl_name_list=tra_lbl_name_list, transform=transforms.Compose([ RescaleT(256), RandomCrop(224), ToTensorLab(flag=0) ])) salobj_dataloader = DataLoader(salobj_dataset, batch_size=batch_size_train, shuffle=True, num_workers=1) # ------- 3. define model -------- # define the net net = BASNet(3, 1) #if torch.cuda.is_available(): # print(torch.cuda.is_available()) net.cuda() # ------- 4. define optimizer -------- print("---define optimizer...") optimizer = optim.Adam(net.parameters(), lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0) # ------- 5. training process -------- print("---start training...") ite_num = 0 running_loss = 0.0 running_tar_loss = 0.0 ite_num4val = 0 for epoch in range(0, epoch_num): net.train() for i, data in enumerate(salobj_dataloader): ite_num = ite_num + 1 ite_num4val = ite_num4val + 1 inputs, labels = data['image'], data['label'] inputs = inputs.type(torch.FloatTensor) labels = labels.type(torch.FloatTensor) # wrap them in Variable # if torch.cuda.is_available(): inputs_v, labels_v = Variable(inputs.cuda(), requires_grad=False), Variable( labels.cuda(), requires_grad=False) # else: # inputs_v, labels_v = Variable(inputs, requires_grad=False), Variable(labels, requires_grad=False) # y zero the parameter gradients optimizer.zero_grad() # forward + backward + optimize d0, d1, d2, d3, d4, d5, d6, d7 = net(inputs_v) loss2, loss = muti_bce_loss_fusion(d0, d1, d2, d3, d4, d5, d6, d7, labels_v) loss.backward() optimizer.step() # # print statistics running_loss += loss.data running_tar_loss += loss2.data # del temporary outputs and loss del d0, d1, d2, d3, d4, d5, d6, d7, loss2, loss print( "[epoch: %3d/%3d, batch: %5d/%5d, ite: %d] train loss: %3f, tar: %3f " % (epoch + 1, epoch_num, (i + 1) * batch_size_train, train_num, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val)) if ite_num % 2000 == 0: # save model every 2000 iterations torch.save( net.state_dict(), model_dir + "basnet_bsi_itr_%d_train_%3f_tar_%3f.pth" % (ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val)) running_loss = 0.0 running_tar_loss = 0.0 net.train() # resume train ite_num4val = 0 print('-------------Congratulations! Training Done!!!-------------')
def train(): if os.name == 'nt': data_dir = 'C:/Users/marky/Documents/Courses/saliency/datasets/DUTS/' else: data_dir = os.getenv( "HOME") + '/Documents/Courses/EE298-CV/finalproj/datasets/DUTS/' tra_image_dir = 'DUTS-TR/DUTS-TR-Image/' tra_label_dir = 'DUTS-TR/DUTS-TR-Mask/' test_image_dir = 'DUTS-TE/DUTS-TE-Image/' test_label_dir = 'DUTS-TE/DUTS-TE-Mask/' image_ext = '.jpg' label_ext = '.png' model_dir = "./saved_models/basnet_bsi_aug/" resume_train = False resume_model_path = model_dir + "basnet_bsi_epoch_81_itr_106839_train_1.511335_tar_0.098392.pth" last_epoch = 1 epoch_num = 100000 batch_size_train = 8 batch_size_val = 1 train_num = 0 val_num = 0 enableInpaintAug = False device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu") # ------- 5. training process -------- print("---start training...") test_increments = 6250 ite_num = 0 running_loss = 0.0 running_tar_loss = 0.0 ite_num4val = 1 next_test = ite_num + 0 visdom_tab_title = "StructArchWithoutStructImgs(WithHFlip)" ############ ############ ############ ############ tra_img_name_list = glob.glob(data_dir + tra_image_dir + '*' + image_ext) print("data_dir + tra_image_dir + '*' + image_ext: ", data_dir + tra_image_dir + '*' + image_ext) test_img_name_list = glob.glob(data_dir + test_image_dir + '*' + image_ext) print("data_dir + test_image_dir + '*' + image_ext: ", data_dir + test_image_dir + '*' + image_ext) tra_lbl_name_list = [] for img_path in tra_img_name_list: img_name = img_path.split("/")[-1] aaa = img_name.split(".") bbb = aaa[0:-1] imidx = bbb[0] for i in range(1, len(bbb)): imidx = imidx + "." + bbb[i] tra_lbl_name_list.append(data_dir + tra_label_dir + imidx + label_ext) test_lbl_name_list = [] for img_path in test_img_name_list: img_name = img_path.split("/")[-1] aaa = img_name.split(".") bbb = aaa[0:-1] imidx = bbb[0] for i in range(1, len(bbb)): imidx = imidx + "." + bbb[i] test_lbl_name_list.append(data_dir + test_label_dir + imidx + label_ext) print("---") print("train images: ", len(tra_img_name_list)) print("train labels: ", len(tra_lbl_name_list)) print("---") print("---") print("test images: ", len(test_img_name_list)) print("test labels: ", len(test_lbl_name_list)) print("---") train_num = len(tra_img_name_list) test_num = len(test_img_name_list) salobj_dataset = SalObjDataset(img_name_list=tra_img_name_list, lbl_name_list=tra_lbl_name_list, transform=transforms.Compose([ RescaleT(256), RandomCrop(224), ToTensorLab(flag=0) ]), category="train", enableInpaintAug=enableInpaintAug) salobj_dataset_test = SalObjDataset(img_name_list=test_img_name_list, lbl_name_list=test_lbl_name_list, transform=transforms.Compose([ RescaleT(256), RandomCrop(224), ToTensorLab(flag=0) ]), category="test", enableInpaintAug=enableInpaintAug) salobj_dataloader = DataLoader(salobj_dataset, batch_size=batch_size_train, shuffle=True, num_workers=1) salobj_dataloader_test = DataLoader(salobj_dataset_test, batch_size=batch_size_val, shuffle=True, num_workers=1) # ------- 3. define model -------- # define the net net = BASNet(3, 1) if resume_train: # print("resume_model_path:", resume_model_path) checkpoint = torch.load(resume_model_path) net.load_state_dict(checkpoint) if torch.cuda.is_available(): net.to(device) # ------- 4. define optimizer -------- print("---define optimizer...") optimizer = optim.Adam(net.parameters(), lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0) plotter = VisdomLinePlotter(env_name=visdom_tab_title) best_ave_mae = 100000 best_max_fmeasure = 0 best_relaxed_fmeasure = 0 best_ave_maxf = 0 best_own_RelaxedFmeasure = 0 for epoch in range(last_epoch - 1, epoch_num): ### Train network train_loss0 = AverageMeter() train_loss1 = AverageMeter() train_loss2 = AverageMeter() train_loss3 = AverageMeter() train_loss4 = AverageMeter() train_loss5 = AverageMeter() train_loss6 = AverageMeter() train_loss7 = AverageMeter() train_struct_loss1 = AverageMeter() train_struct_loss2 = AverageMeter() train_struct_loss3 = AverageMeter() train_struct_loss4 = AverageMeter() train_struct_loss5 = AverageMeter() train_struct_loss6 = AverageMeter() train_struct_loss7 = AverageMeter() test_loss0 = AverageMeter() test_loss1 = AverageMeter() test_loss2 = AverageMeter() test_loss3 = AverageMeter() test_loss4 = AverageMeter() test_loss5 = AverageMeter() test_loss6 = AverageMeter() test_loss7 = AverageMeter() test_struct_loss1 = AverageMeter() test_struct_loss2 = AverageMeter() test_struct_loss3 = AverageMeter() test_struct_loss4 = AverageMeter() test_struct_loss5 = AverageMeter() test_struct_loss6 = AverageMeter() test_struct_loss7 = AverageMeter() average_mae = AverageMeter() average_maxf = AverageMeter() average_relaxedf = AverageMeter() average_own_RelaxedFMeasure = AverageMeter() net.train() for i, data in enumerate(salobj_dataloader): ite_num = ite_num + 1 ite_num4val = ite_num4val + 1 inputs, labels, labels_struct = data['image'], data['label'], data[ 'label2'] inputs = inputs.type(torch.FloatTensor) labels = labels.type(torch.FloatTensor) labels_struct = labels_struct.type(torch.FloatTensor) # wrap them in Variable if torch.cuda.is_available(): inputs_v, labels_v, labels_struct_v = Variable( inputs.to(device), requires_grad=False), Variable( labels.to(device), requires_grad=False), Variable( labels_struct.to(device), requires_grad=False) else: inputs_v, labels_v, labels_struct_v = Variable( inputs, requires_grad=False), Variable( labels, requires_grad=False), Variable(labels_struct, requires_grad=False) # y zero the parameter gradients optimizer.zero_grad() # forward + backward + optimize d0, d1, d2, d3, d4, d5, d6, d7, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct = net( inputs_v) loss2, loss = muti_bce_loss_fusion( d0, d1, d2, d3, d4, d5, d6, d7, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct, labels_v, train_loss0, train_loss1, train_loss2, train_loss3, train_loss4, train_loss5, train_loss6, train_loss7, train_struct_loss1, train_struct_loss2, train_struct_loss3, train_struct_loss4, train_struct_loss5, train_struct_loss6, train_struct_loss7) loss.backward() optimizer.step() # # print statistics running_loss += loss.data running_tar_loss += loss2.data # del temporary outputs and loss del d0, d1, d2, d3, d4, d5, d6, d7, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct, loss2, loss print( "[train epoch: %3d/%3d, batch: %5d/%5d, ite: %d] train loss: %3f, tar: %3f " % (epoch + 1, epoch_num, (i + 1) * batch_size_train, train_num, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val)) plotter.plot('loss0', 'train', 'Main Loss 0', epoch + 1, float(train_loss0.avg)) plotter.plot('loss1', 'train', 'Main Loss 1', epoch + 1, float(train_loss1.avg)) plotter.plot('loss2', 'train', 'Main Loss 2', epoch + 1, float(train_loss2.avg)) plotter.plot('loss3', 'train', 'Main Loss 3', epoch + 1, float(train_loss3.avg)) plotter.plot('loss4', 'train', 'Main Loss 4', epoch + 1, float(train_loss4.avg)) plotter.plot('loss5', 'train', 'Main Loss 5', epoch + 1, float(train_loss5.avg)) plotter.plot('loss6', 'train', 'Main Loss 6', epoch + 1, float(train_loss6.avg)) plotter.plot('loss7', 'train', 'Main Loss 7', epoch + 1, float(train_loss7.avg)) plotter.plot('structloss1', 'train', 'Struct Loss 1', epoch + 1, float(train_struct_loss1.avg)) plotter.plot('structloss2', 'train', 'Struct Loss 2', epoch + 1, float(train_struct_loss2.avg)) plotter.plot('structloss3', 'train', 'Struct Loss 3', epoch + 1, float(train_struct_loss3.avg)) plotter.plot('structloss4', 'train', 'Struct Loss 4', epoch + 1, float(train_struct_loss4.avg)) plotter.plot('structloss5', 'train', 'Struct Loss 5', epoch + 1, float(train_struct_loss5.avg)) plotter.plot('structloss6', 'train', 'Struct Loss 6', epoch + 1, float(train_struct_loss6.avg)) plotter.plot('structloss7', 'train', 'Struct Loss 7', epoch + 1, float(train_struct_loss7.avg)) ### Validate model print("---Evaluate model---") if ite_num >= next_test: # test and save model 10000 iterations, due to very large DUTS-TE dataset next_test = ite_num + test_increments net.eval() max_epoch_fmeasure = 0 for i, data in enumerate(salobj_dataloader_test): inputs, labels = data['image'], data['label'] inputs = inputs.type(torch.FloatTensor) labels = labels.type(torch.FloatTensor) if torch.cuda.is_available(): inputs_v, labels_v = Variable( inputs.to(device), requires_grad=False), Variable(labels.to(device), requires_grad=False) else: inputs_v, labels_v = Variable( inputs, requires_grad=False), Variable(labels, requires_grad=False) d0, d1, d2, d3, d4, d5, d6, d7, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct = net( inputs_v) pred = d0[:, 0, :, :] pred = normPRED(pred) pred = pred.squeeze() predict_np = pred.cpu().data.numpy() im = Image.fromarray(predict_np * 255).convert('RGB') img_name = test_img_name_list[i] image = cv2.imread(img_name) imo = im.resize((image.shape[1], image.shape[0]), resample=Image.BILINEAR) imo = imo.convert("L") ### Convert to grayscale 1-channel resizedImg_np = np.array( imo) ### Result is 2D numpy array predicted salient map img__lbl_name = test_lbl_name_list[i] gt_img = np.array(Image.open(img__lbl_name).convert( "L")) ### Ground truth salient map ### Compute metrics result_mae = getMAE(gt_img, resizedImg_np) average_mae.update(result_mae, 1) precision, recall = getPRCurve(gt_img, resizedImg_np) result_maxfmeasure = getMaxFMeasure(precision, recall) result_maxfmeasure = result_maxfmeasure.mean() average_maxf.update(result_maxfmeasure, 1) if (result_maxfmeasure > max_epoch_fmeasure): max_epoch_fmeasure = result_maxfmeasure result_relaxedfmeasure = getRelaxedFMeasure( gt_img, resizedImg_np) result_ownrelaxedfmeasure = own_RelaxedFMeasure( gt_img, resizedImg_np) average_relaxedf.update(result_relaxedfmeasure, 1) average_own_RelaxedFMeasure.update(result_ownrelaxedfmeasure, 1) loss2, loss = muti_bce_loss_fusion( d0, d1, d2, d3, d4, d5, d6, d7, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct, labels_v, test_loss0, test_loss1, test_loss2, test_loss3, test_loss4, test_loss5, test_loss6, test_loss7, test_struct_loss1, test_struct_loss2, test_struct_loss3, test_struct_loss4, test_struct_loss5, test_struct_loss6, test_struct_loss7) del d0, d1, d2, d3, d4, d5, d6, d7, d1_struct, d2_struct, d3_struct, d4_struct, d5_struct, d6_struct, d7_struct, loss2, loss print( "[test epoch: %3d/%3d, batch: %5d/%5d, ite: %d] test loss: %3f, tar: %3f " % (epoch + 1, epoch_num, (i + 1) * batch_size_val, test_num, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val)) model_name = model_dir + "basnet_bsi_epoch_%d_itr_%d_train_%3f_tar_%3f.pth" % ( epoch + 1, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val) torch.save(net.state_dict(), model_name) running_loss = 0.0 running_tar_loss = 0.0 net.train() # resume train ite_num4val = 1 if (average_mae.avg < best_ave_mae): best_ave_mae = average_mae.avg newname = model_dir + "bestMAE/basnet_bsi_epoch_%d_itr_%d_train_%3f_tar_%3f_mae_%3f.pth" % ( epoch + 1, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val, best_ave_mae) fold_dir = newname.rsplit("/", 1) if not os.path.isdir(fold_dir[0]): os.mkdir(fold_dir[0]) copyfile(model_name, newname) if (max_epoch_fmeasure > best_max_fmeasure): best_max_fmeasure = max_epoch_fmeasure newname = model_dir + "bestEpochMaxF/basnet_bsi_epoch_%d_itr_%d_train_%3f_tar_%3f_maxfmeas_%3f.pth" % ( epoch + 1, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val, best_max_fmeasure) fold_dir = newname.rsplit("/", 1) if not os.path.isdir(fold_dir[0]): os.mkdir(fold_dir[0]) copyfile(model_name, newname) if (average_maxf.avg > best_ave_maxf): best_ave_maxf = average_maxf.avg newname = model_dir + "bestAveMaxF/basnet_bsi_epoch_%d_itr_%d_train_%3f_tar_%3f_avemfmeas_%3f.pth" % ( epoch + 1, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val, best_ave_maxf) fold_dir = newname.rsplit("/", 1) if not os.path.isdir(fold_dir[0]): os.mkdir(fold_dir[0]) copyfile(model_name, newname) if (average_relaxedf.avg > best_relaxed_fmeasure): best_relaxed_fmeasure = average_relaxedf.avg newname = model_dir + "bestAveRelaxF/basnet_bsi_epoch_%d_itr_%d_train_%3f_tar_%3f_averelaxfmeas_%3f.pth" % ( epoch + 1, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val, best_relaxed_fmeasure) fold_dir = newname.rsplit("/", 1) if not os.path.isdir(fold_dir[0]): os.mkdir(fold_dir[0]) copyfile(model_name, newname) if (average_own_RelaxedFMeasure.avg > best_own_RelaxedFmeasure): best_own_RelaxedFmeasure = average_own_RelaxedFMeasure.avg newname = model_dir + "bestOwnRelaxedF/basnet_bsi_epoch_%d_itr_%d_train_%3f_tar_%3f_averelaxfmeas_%3f.pth" % ( epoch + 1, ite_num, running_loss / ite_num4val, running_tar_loss / ite_num4val, best_own_RelaxedFmeasure) fold_dir = newname.rsplit("/", 1) if not os.path.isdir(fold_dir[0]): os.mkdir(fold_dir[0]) copyfile(model_name, newname) plotter.plot('loss0', 'test', 'Main Loss 0', epoch + 1, float(test_loss0.avg)) plotter.plot('loss1', 'test', 'Main Loss 1', epoch + 1, float(test_loss1.avg)) plotter.plot('loss2', 'test', 'Main Loss 2', epoch + 1, float(test_loss2.avg)) plotter.plot('loss3', 'test', 'Main Loss 3', epoch + 1, float(test_loss3.avg)) plotter.plot('loss4', 'test', 'Main Loss 4', epoch + 1, float(test_loss4.avg)) plotter.plot('loss5', 'test', 'Main Loss 5', epoch + 1, float(test_loss5.avg)) plotter.plot('loss6', 'test', 'Main Loss 6', epoch + 1, float(test_loss6.avg)) plotter.plot('loss7', 'test', 'Main Loss 7', epoch + 1, float(test_loss7.avg)) plotter.plot('structloss1', 'test', 'Struct Loss 1', epoch + 1, float(test_struct_loss1.avg)) plotter.plot('structloss2', 'test', 'Struct Loss 2', epoch + 1, float(test_struct_loss2.avg)) plotter.plot('structloss3', 'test', 'Struct Loss 3', epoch + 1, float(test_struct_loss3.avg)) plotter.plot('structloss4', 'test', 'Struct Loss 4', epoch + 1, float(test_struct_loss4.avg)) plotter.plot('structloss5', 'test', 'Struct Loss 5', epoch + 1, float(test_struct_loss5.avg)) plotter.plot('structloss6', 'test', 'Struct Loss 6', epoch + 1, float(test_struct_loss6.avg)) plotter.plot('structloss7', 'test', 'Struct Loss 7', epoch + 1, float(test_struct_loss7.avg)) plotter.plot('mae', 'test', 'Average Epoch MAE', epoch + 1, float(average_mae.avg)) plotter.plot('max_maxf', 'test', 'Max Max Epoch F-Measure', epoch + 1, float(max_epoch_fmeasure)) plotter.plot('ave_maxf', 'test', 'Average Max F-Measure', epoch + 1, float(average_maxf.avg)) plotter.plot('ave_relaxedf', 'test', 'Average Relaxed F-Measure', epoch + 1, float(average_relaxedf.avg)) plotter.plot('own_RelaxedFMeasure', 'test', 'Own Average Relaxed F-Measure', epoch + 1, float(average_own_RelaxedFMeasure.avg)) print('-------------Congratulations! Training Done!!!-------------')