diff --git a/modules/deeplearning/icing_cnn.py b/modules/deeplearning/icing_cnn.py index 3c0336342745d914859f0b5e6cac868548b7896a..fcadd0f36db14ee8be919d3e4d323e8bf3ed7c92 100644 --- a/modules/deeplearning/icing_cnn.py +++ b/modules/deeplearning/icing_cnn.py @@ -18,7 +18,7 @@ PROC_BATCH_SIZE = 2046 PROC_BATCH_BUFFER_SIZE = 50000 NumLabels = 1 BATCH_SIZE = 256 -NUM_EPOCHS = 60 +NUM_EPOCHS = 80 TRACK_MOVING_AVERAGE = False @@ -243,7 +243,7 @@ class IcingIntensityNN: dataset = dataset.map(self.data_function, num_parallel_calls=8) self.test_dataset = dataset - def setup_pipeline(self, filename, train_idxs=None, test_idxs=None): + def setup_pipeline(self, filename): self.filename = filename self.h5f = h5py.File(filename, 'r') time = self.h5f['time'] @@ -592,16 +592,16 @@ class IcingIntensityNN: self.predict(mini_batch_test) print('loss, acc: ', self.test_loss.result(), self.test_accuracy.result()) - def run(self, filename, filename_l1b=None, train_dict=None, valid_dict=None): + def run(self, filename, filename_l1b=None): with tf.device('/device:GPU:'+str(self.gpu_device)): - self.setup_pipeline(filename, train_idxs=train_dict, test_idxs=valid_dict) + self.setup_pipeline(filename) self.build_model() self.build_training() self.build_evaluation() self.do_training() - def run_restore(self, filename, ckpt_dir, train_dict=None, valid_dict=None): - self.setup_pipeline(filename, train_idxs=train_dict, test_idxs=valid_dict) + def run_restore(self, filename, ckpt_dir): + self.setup_pipeline(filename) self.build_model() self.build_training() self.build_evaluation()