runtime error

3G [00:13<00:00, 80.1MB/s] Downloading pytorch_model.bin: 100%|█████████▉| 1.33G/1.33G [00:13<00:00, 94.9MB/s] Downloading pytorch_model.bin: 100%|██████████| 1.33G/1.33G [00:13<00:00, 98.4MB/s] Some weights of VisionEncoderDecoderModel were not initialized from the model checkpoint at microsoft/trocr-base-handwritten and are newly initialized: ['encoder.pooler.dense.weight', 'encoder.pooler.dense.bias'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. Downloading (…)neration_config.json: 0%| | 0.00/190 [00:00<?, ?B/s] Downloading (…)neration_config.json: 100%|██████████| 190/190 [00:00<00:00, 7.39kB/s] Traceback (most recent call last): File "app.py", line 4, in <module> ocr = OCR.load_models() File "/home/user/.local/lib/python3.8/site-packages/craft_hw_ocr/OCR.py", line 46, in load_models craft = Craft(output_dir=None, File "/home/user/.local/lib/python3.8/site-packages/craft_text_detector/__init__.py", line 78, in __init__ self.load_craftnet_model(weight_path_craft_net) File "/home/user/.local/lib/python3.8/site-packages/craft_text_detector/__init__.py", line 87, in load_craftnet_model self.craft_net = load_craftnet_model(self.cuda, weight_path=weight_path) File "/home/user/.local/lib/python3.8/site-packages/craft_text_detector/craft_utils.py", line 55, in load_craftnet_model from craft_text_detector.models.craftnet import CraftNet File "/home/user/.local/lib/python3.8/site-packages/craft_text_detector/models/craftnet.py", line 11, in <module> from craft_text_detector.models.basenet.vgg16_bn import vgg16_bn, init_weights File "/home/user/.local/lib/python3.8/site-packages/craft_text_detector/models/basenet/vgg16_bn.py", line 7, in <module> from torchvision.models.vgg import model_urls ImportError: cannot import name 'model_urls' from 'torchvision.models.vgg' (/home/user/.local/lib/python3.8/site-packages/torchvision/models/vgg.py)

Container logs: