'update_lr', 1e-3,
'step size alpha for inner gradient update.') # 0.1 for omniglot
flags.DEFINE_integer('num_updates', 1,
'number of inner gradient updates during training.')
flags.DEFINE_integer(
'sine_seed', '1',
'seed for the random operations inside sine generator; sinuosidal regression expt'
)
## Model options
flags.DEFINE_string('norm', 'batch_norm', 'batch_norm, layer_norm, or None')
flags.DEFINE_integer(
'num_filters', 64,
'number of filters for conv nets -- 32 for miniimagenet, 64 for omiglot.')
flags.DEFINE_bool(
'conv', True,
'whether or not to use a convolutional network, only applicable in some cases'
)
flags.DEFINE_bool(
'max_pool', False,
'Whether or not to use max pooling rather than strided convolutions')
flags.DEFINE_bool(
'stop_grad', False,
'if True, do not use second derivatives in meta-optimization (for speed)')
## Logging, saving, and testing options
flags.DEFINE_bool('log', True,
'if false, do not log summaries, for debugging code.')
flags.DEFINE_string('logdir', '/tmp/data',
'directory for summaries and checkpoints.')
flags.DEFINE_bool('resume', True,
'resume training if there is a model available')
'V': 99.06841,
'Y': 163.06333,
'M(ox)': 147.035405,
'groupCH3': 14.01565,
'groupOH': 17.00274,
'groupH': 1.007825,
'groupH2O': 18.01057,
'groupCH3CO': 42.01057,
'groupO': 15.994915,
'groupNH3': 17.02655
}
FLAGS = flags.FLAGS
flags.DEFINE_string('input_data', '', 'Input data filepath.')
flags.DEFINE_string('output_data_dir', '', 'Input data filepath.')
flags.DEFINE_bool('clean_peptides', False,
'True if peptide modifications are in [x] format.')
flags.DEFINE_string('sequence_col', _MOD_SEQUENCE,
'Modified sequence column name in the input file.')
flags.DEFINE_string('charge_col', _CHARGE,
'Charge column name in the input file.')
flags.DEFINE_string('fragmentation_col', _FRAGMENTATION,
'Fragmentation column name in the input file.')
flags.DEFINE_string('analyzer_col', _MASS_ANALYZER,
'Mass analyzer column name in the input file.')
def generate_json_inputs(data, encoding):
"""Generates inputs to-be stored into a JSON file.
Args:
data: A pandas dataframe with modified sequence and metadata features.
def define():
"""Define common flags."""
# yapf: disable
# common_flags.define() may be called multiple times in unit tests.
global _common_flags_defined
if _common_flags_defined:
return
_common_flags_defined = True
flags.DEFINE_integer('batch_size', 32,
'Batch size.')
flags.DEFINE_integer('crop_width', None,
'Width of the central crop for images.')
flags.DEFINE_integer('crop_height', None,
'Height of the central crop for images.')
flags.DEFINE_string('train_log_dir', '/tmp/attention_ocr/train',
'Directory where to write event logs.')
flags.DEFINE_string('dataset_name', 'fsns',
'Name of the dataset. Supported: fsns')
flags.DEFINE_string('split_name', 'train',
'Dataset split name to run evaluation for: test,train.')
flags.DEFINE_string('dataset_dir', None,
'Dataset root folder.')
flags.DEFINE_string('checkpoint', '',
'Path for checkpoint to restore weights from.')
flags.DEFINE_string('master',
'',
'BNS name of the TensorFlow master to use.')
# Model hyper parameters
flags.DEFINE_float('learning_rate', 0.004,
'learning rate')
flags.DEFINE_string('optimizer', 'momentum',
'the optimizer to use')
flags.DEFINE_float('momentum', 0.9,
'momentum value for the momentum optimizer if used')
flags.DEFINE_bool('use_augment_input', True,
'If True will use image augmentation')
# Method hyper parameters
# conv_tower_fn
flags.DEFINE_string('final_endpoint', 'Mixed_5d',
'Endpoint to cut inception tower')
# sequence_logit_fn
flags.DEFINE_bool('use_attention', True,
'If True will use the attention mechanism')
flags.DEFINE_bool('use_autoregression', True,
'If True will use autoregression (a feedback link)')
flags.DEFINE_integer('num_lstm_units', 256,
'number of LSTM units for sequence LSTM')
flags.DEFINE_float('weight_decay', 0.00004,
'weight decay for char prediction FC layers')
flags.DEFINE_float('lstm_state_clip_value', 10.0,
'cell state is clipped by this value prior to the cell'
' output activation')
# 'sequence_loss_fn'
flags.DEFINE_float('label_smoothing', 0.1,
'weight for label smoothing')
flags.DEFINE_bool('ignore_nulls', True,
'ignore null characters for computing the loss')
flags.DEFINE_bool('average_across_timesteps', False,
'divide the returned cost by the total label weight')
common_flags.define()
flags.DEFINE_string('export_dir', None, 'Directory to export model files to.')
flags.DEFINE_integer(
'image_width', None,
'Image width used during training (or crop width if used)'
' If not set, the dataset default is used instead.')
flags.DEFINE_integer(
'image_height', None,
'Image height used during training(or crop height if used)'
' If not set, the dataset default is used instead.')
flags.DEFINE_string('work_dir', '/tmp',
'A directory to store temporary files.')
flags.DEFINE_integer('version_number', 1, 'Version number of the model')
flags.DEFINE_bool(
'export_for_serving', True,
'Whether the exported model accepts serialized tf.Example '
'protos as input')
def get_checkpoint_path():
"""Returns a path to a checkpoint based on specified commandline flags.
In order to specify a full path to a checkpoint use --checkpoint flag.
Alternatively, if --train_log_dir was specified it will return a path to the
most recent checkpoint.
Raises:
ValueError: in case it can't find a checkpoint.
Returns:
A string.
from tensorflow.keras.applications.resnet50 import ResNet50
from tensorflow.keras.layers import Input
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions
from tensorflow.compat.v1 import flags
from tensorflow.keras.optimizers import RMSprop
from dataset import synth_input_fn
from dataset import input_fn, NUM_IMAGES
from dataset import get_images_infor_from_file, ImagenetSequence
keras = tf.keras
flags.DEFINE_string('model', './train_dir/resnet50_model_195.h5',
'TensorFlow \'GraphDef\' file to load.')
flags.DEFINE_bool('eval_tfrecords', True, 'If True then use tf_records data .')
flags.DEFINE_string('data_dir', '/data3/datasets/Kaggle/fruits-360/tf_records',
'The directory where put the eval images')
flags.DEFINE_bool('eval_images', False, 'If True then use tf_records data .')
flags.DEFINE_string('eval_image_path',
'/data3/datasets/Kaggle/fruits-360/val_for_tf2',
'The directory where put the eval images')
flags.DEFINE_string('eval_image_list',
'/data3/datasets/Kaggle/fruits-360/val_labels.txt',
'file has validation images list')
flags.DEFINE_string('save_path', "train_dir", 'The directory where save model')
flags.DEFINE_string('filename', "resnet50_model_{epoch}.h5",
'The name of sved model')
flags.DEFINE_integer('label_offset', 1, 'label offset')
flags.DEFINE_string('gpus', '0', 'The gpus used for running evaluation.')
flags.DEFINE_bool('eval_only', False,
'seconds.')
flags.DEFINE_integer('save_interval_secs', 600,
'Frequency in seconds of saving the model.')
flags.DEFINE_integer('max_number_of_steps', int(1e10),
'The maximum number of gradient steps.')
flags.DEFINE_string('checkpoint_inception', '',
'Checkpoint to recover inception weights from.')
flags.DEFINE_float('clip_gradient_norm', 2.0,
'If greater than 0 then the gradients would be clipped by '
'it.')
flags.DEFINE_bool('sync_replicas', False,
'If True will synchronize replicas during training.')
flags.DEFINE_integer('replicas_to_aggregate', 1,
'The number of gradients updates before updating params.')
flags.DEFINE_integer('total_num_replicas', 1,
'Total number of worker replicas.')
flags.DEFINE_integer('startup_delay_steps', 15,
'Number of training steps between replicas startup.')
flags.DEFINE_boolean('reset_train_dir', False,
'If true will delete all files in the train_log_dir')
flags.DEFINE_boolean('show_graph_stats', False,
'Output model size stats to stderr.')
_LENGTH = 'Length'
_POSITION_COL = 'FragmentNumber'
_ION_COL = 'FragmentType'
_ABUNDANCE_COL = 'RelativeIntensity'
_LOSS_TYPE = 'FragmentLossType'
_FRAG_CHARGE = 'FragmentCharge'
FLAGS = flags.FLAGS
flags.DEFINE_string('metadata_file', None, 'Path to a TSV file with metadata.')
flags.DEFINE_string('input_data_pattern', None, 'Input data filename pattern.')
flags.DEFINE_enum('label_dim', '2', ['2', '6'],
'Number of features in the output/label time step')
flags.DEFINE_string('output_data_dir', None,
'Directory with prediction outputs.')
flags.DEFINE_bool('neutral_losses', False,
'True if H2O and NH3 losses are modeled.')
flags.DEFINE_bool(
'batch_prediction', True,
'True if batch prediction instead of online was used to generate outputs.')
flags.DEFINE_string(
'add_input_data_pattern', None,
('Input data filename pattern for additional features to-be included to '
'the final outptu. These inputs should be formatted in the same way as'
'the model outputs - ie, JSON format with "key" and "output" values,'
'where the key is an integer and output is a list of feature values.'))
flags.DEFINE_list('add_feature_names', None,
'A comma-separated list of additional feature names.')
def reformat_outputs(row, label_dim, neutral_losses):
"""Reformats output from the spectral model into a TSV shape.
