runtime error

███▉ | 326M/363M [00:07<00:00, 39.1MB/s] Downloading: 92%|█████████▏| 335M/363M [00:07<00:00, 48.4MB/s] Downloading: 94%|█████████▍| 342M/363M [00:07<00:00, 43.5MB/s] Downloading: 95%|█████████▌| 347M/363M [00:07<00:00, 40.5MB/s] Downloading: 98%|█████████▊| 356M/363M [00:08<00:00, 51.2MB/s] Downloading: 100%|██████████| 363M/363M [00:08<00:00, 44.9MB/s] Downloading: 0%| | 0.00/6.61k [00:00<?, ?B/s] Downloading: 100%|██████████| 6.61k/6.61k [00:00<00:00, 3.95MB/s] 2023-11-27 22:54:28.373226: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory 2023-11-27 22:54:28.373259: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303) 2023-11-27 22:54:28.373283: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (r-mikachou-dog-breed-identification-jyyq50l6-6f66d-w4gzh): /proc/driver/nvidia/version does not exist 2023-11-27 22:54:28.373559: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. Traceback (most recent call last): File "/home/user/app/app.py", line 9, in <module> model = tf.keras.models.load_model(tf_model) File "/home/user/.local/lib/python3.10/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler raise e.with_traceback(filtered_tb) from None File "/home/user/.local/lib/python3.10/site-packages/keras/utils/generic_utils.py", line 793, in func_load code = marshal.loads(raw_code) ValueError: bad marshal data (unknown type code)

Container logs: