def process_image(image_path): """ Scales, crops, and normalizes a PIL image for a PyTorch model, returns an Numpy array """ with Image.open(image_path) as image: transform = get_test_transforms() image = transform(image).numpy() return image
map_location=device)) model2 = Darknet(os.path.join( BASE_DIR, "yolo_v3/config/yolov3-custom.cfg")).to(device) model2.load_state_dict( torch.load(os.path.join(models_path, "yolo_v3_4_20.pt"), map_location=device)) model3 = Darknet(os.path.join( BASE_DIR, "yolo_v3/config/yolov3-custom.cfg")).to(device) model3.load_state_dict( torch.load(os.path.join(models_path, "yolo_v3_4_25.pt"), map_location=device)) dataset = MyTestDataset(split='stage1_train', transforms=get_test_transforms(rescale_size=(416, 416))) test_loader = DataLoader(dataset, batch_size=1, num_workers=0, shuffle=False) model.eval() model2.eval() model3.eval() for i, (image, targets) in enumerate(test_loader): image = image[0].to(device=device) name = targets["name"][0] start_time = time.time() with torch.no_grad(): outputs = model(image)
# image_copy.show() # image_copy.save(os.path.join(images_path, f"faster_rcnn/{attempt}/images/{name}.png")) print(f"{name}, time: {elapsed_time}") plt.imshow(image_copy) plt.show() break if __name__ == "__main__": # torch.manual_seed(4) from models import model attempt = 7 model_name = "faster_rcnn_7_30.pt" device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print(f"Running on {device}...") model.load_state_dict( torch.load(os.path.join(models_path, "faster_rcnn_7_30.pt"), map_location=device)) dataset = MyTestDataset(split='stage1_test', transforms=get_test_transforms(rescale_size=(256, 256))) test_loader = DataLoader(dataset, batch_size=1, num_workers=0, shuffle=True) predict(model, test_loader)
from yolo_v3.models import Darknet from unet.models import UNet faster_name = "faster_rcnn.pt" yolo_name = "yolo_v3.pt" unet_name = "unet.pt" device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print(f"Running on {device}") print(f"Loading {faster_name}") faster.load_state_dict( torch.load(os.path.join(models_path, faster_name), map_location=device)) faster.to(device=device) dataset = MyDemoDataset(transforms=get_test_transforms(rescale_size=(256, 256))) faster_loader = DataLoader(dataset, batch_size=1, num_workers=0, shuffle=False) print(f"Loading {yolo_name}") yolo = Darknet(os.path.join(BASE_DIR, "yolo_v3/config/yolov3-custom.cfg")) yolo.load_state_dict( torch.load(os.path.join(models_path, yolo_name), map_location=device)) yolo.to(device=device) dataset = MyDemoDataset(transforms=get_test_transforms(rescale_size=(416, 416))) yolo_loader = DataLoader(dataset, batch_size=1, num_workers=0,