Hello,
I get this error when trying to just run with the instructions written in the repo readme.
_File "run_train_eval_exp.py", line 156, in
main()
File "run_train_eval_exp.py", line 48, in main
X_train, y_train, X_test, y_test = load_dataset(cfg)
File "run_train_eval_exp.py", line 56, in load_dataset
dataset = utils.load_dataset(cfg.DATASET.NAME)
File "/neural_kernels_code/utils.py", line 118, in load_dataset
return np.load(io.BytesIO(wrapper.get(key="datasets/cifar_10_zca_augmented_extra_zca_augment_en9fKkGMMg.npz")))
File "/neural_kernels_code/s3_utils.py", line 453, in get
return self.get_multiple([key], verbose=verbose, skip_modification_time_check=skip_modification_time_check)[key]
File "/neural_kernels_code/s3_utils.py", line 473, in get_multiple
skip_modification_time_check=cur_skip_time_check)
File "/neural_kernels_code/s3_utils.py", line 140, in get_s3_object_bytes_parallel
raise exc
File "/neural_kernels_code/s3_utils.py", line 134, in get_s3_object_bytes_parallel
success = future.result()
File "/root/conda/lib/python3.6/concurrent/futures/_base.py", line 425, in result
return self.__get_result()
File "/root/conda/lib/python3.6/concurrent/futures/_base.py", line 384, in __get_result
raise self.exception
File "/root/conda/lib/python3.6/concurrent/futures/thread.py", line 56, in run
result = self.fn(*self.args, **self.kwargs)
File "/neural_kernels_code/s3_utils.py", line 124, in cur_download_file
thread_local=tl)
File "/neural_kernels_code/s3_utils.py", line 353, in download_s3_file_with_backoff
raise Exception('download backoff failed ' + ' ' + str(key) + ' ' + str(delay))
Exception: download backoff failed datasets/cifar_10_zca_augmented_extra_zca_augment_en9fKkGMMg.npz 4.000000000000001
Any suggestions how I can pass through this?