diff --git a/modules/deeplearning/icing.py b/modules/deeplearning/icing.py index 5e67a711cc7e8ae11adebe27909f125e9ae81d6c..c5a651e80a722cdb4e02a9e8be1913394c17dcb4 100644 --- a/modules/deeplearning/icing.py +++ b/modules/deeplearning/icing.py @@ -45,7 +45,7 @@ abi_half_width = {'08': 12, '14': 12, '02': 48, '11': 12, '13': 12, '15': 12, '1 #abi_half_width = {'08': 6, '14': 6, '02': 24, '11': 6, '13': 6, '15': 6, '16': 6, '09': 6, '10': 6} #abi_half_width = {'08': 3, '14': 3, '02': 12, '11': 3, '13': 3, '15': 3, '16': 3, '09': 3, '10': 3} abi_stride = {'08': 1, '14': 1, '02': 4, '11': 1, '13': 1, '15': 1, '16': 1, '09': 1, '10': 1} -img_width = 24 +img_width = 16 #img_width = 12 #img_width = 6 @@ -204,10 +204,14 @@ class IcingIntensityNN: # nda = do_normalize(nda) data.append(nda) data = np.stack(data) - data = np.transpose(data, axes=(1,0)) + data = data.astype(np.float32) + data = np.transpose(data, axes=(1, 0)) + label = self.h5f['icing_intensity'][nd_keys] + label = label.astype(np.int32) label = np.where(label == -1, 0, label) - # binary + + # binary, two class label = np.where(label != 0, 1, label) # TODO: Implement in memory cache @@ -228,7 +232,7 @@ class IcingIntensityNN: @tf.function(input_signature=[tf.TensorSpec(None, tf.int32)]) def data_function(self, indexes): - out = tf.numpy_function(self.get_in_mem_data_batch, [indexes], [tf.float64, tf.float64, tf.int32]) + out = tf.numpy_function(self.get_in_mem_data_batch, [indexes], [tf.float32, tf.float32, tf.int32]) return out def get_train_dataset(self, indexes):