Last active
June 7, 2022 10:46
-
-
Save deepanshu-yadav/154c4acfc79d22acaf6b8d2865dfd2e9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import glob | |
| from sklearn.preprocessing import MinMaxScaler | |
| def npy_header_offset(npy_path): | |
| """Gives the no of header bytes inside a numpy file.""" | |
| with open(str(npy_path), 'rb') as f: | |
| if f.read(6) != b'\x93NUMPY': | |
| raise ValueError('Invalid NPY file.') | |
| version_major, version_minor = f.read(2) | |
| if version_major == 1: | |
| header_len_size = 2 | |
| elif version_major == 2: | |
| header_len_size = 4 | |
| else: | |
| raise ValueError('Unknown NPY file version {}.{}'. | |
| format(version_major, version_minor)) | |
| header_len = sum(b << (8 * i) for i, b in enumerate( | |
| f.read(header_len_size))) | |
| header = f.read(header_len) | |
| if not header.endswith(b'\n'): | |
| raise ValueError('Invalid NPY file.') | |
| return f.tell() | |
| # Following code fits the min max scaler, | |
| # as well as gets the total number of examples | |
| # for training and validation. | |
| training_files = glob.glob(os.path.join(train_dir, '*')) | |
| validation_files = glob.glob(os.path.join(validation_dir, '*')) | |
| min_max_scaler_train = MinMaxScaler() | |
| BATCH_SIZE = 32 | |
| NO_OF_EPOCHS = 3 | |
| total_examples_train = 0 | |
| for train_file_name in training_files: | |
| file_np = np.load(train_file_name) | |
| rows = file_np.shape[0] | |
| total_examples_train += rows | |
| # we will fit the min max scaler to training data here. | |
| # Notice we will use partial fit for large data. | |
| min_max_scaler_train.partial_fit(file_np) | |
| total_examples_validation = 0 | |
| for validation_file_name in validation_files: | |
| file_np = np.load(validation_file_name) | |
| rows = file_np.shape[0] | |
| total_examples_validation += rows |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment