add arg to adjust learning rate

aimodel/src/lib/ai/model_rainfallwater_mono.py

@@ -8,15 +8,18 @@ from .components.convnext_inverse import do_convnext_inverse
 from .components.LayerStack2Image import LayerStack2Image
 from .components.LossCrossentropy import LossCrossentropy
 
-def model_rainfallwater_mono(metadata, shape_water_out, model_arch_enc="convnext_xtiny", model_arch_dec="convnext_i_xtiny", feature_dim=512, batch_size=64, water_bins=2):
+def model_rainfallwater_mono(metadata, shape_water_out, model_arch_enc="convnext_xtiny", model_arch_dec="convnext_i_xtiny", feature_dim=512, batch_size=64, water_bins=2, learning_rate=None):
 	"""Makes a new rainfall / waterdepth mono model.
 
 	Args:
 		metadata (dict): A dictionary of metadata about the dataset to use to build the model with.
 		shape_water_out (int[]): The width and height (in that order) that should dictate the output shape of the segmentation head. CURRENTLY NOT USED.
-		model_arch (str, optional): The architecture code for the underlying (inverted) ConvNeXt model. Defaults to "convnext_i_xtiny".
+		feature_dim	(int, optiona): The size of the bottleneck. Defaults to 512.
+		model_arch_enc (str, optional): The architecture code for the underlying (inverted) ConvNeXt model for the encoder. Defaults to "convnext_xtiny".
+		model_arch_dec (str, optional): The architecture code for the underlying (inverted) ConvNeXt model for the decoder. Defaults to "convnext_i_xtiny".
 		batch_size (int, optional): The batch size. Reduce to save memory. Defaults to 64.
 		water_bins (int, optional): The number of classes that the water depth output oft he segmentation head should be binned into. Defaults to 2.
+		learning_rate (float, optional): The (initial) learning rate. YOU DO NOT USUALLY NEED TO CHANGE THIS. For experimental purposes only. Defaults to None, which means it will be determined automatically.
 
 	Returns:
 		tf.keras.Model: The new model, freshly compiled for your convenience! :D
@@ -70,8 +73,11 @@ def model_rainfallwater_mono(metadata, shape_water_out, model_arch_enc="convnext
 		outputs = layer_next
 	)
 	
+	optimizer = "Adam"
+	if learning_rate is not None:
+		optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
 	model.compile(
-		optimizer="Adam",
+		optimizer=optimizer,
 		loss=LossCrossentropy(batch_size=batch_size),
 		# loss=tf.keras.losses.CategoricalCrossentropy(),
 		metrics=[tf.keras.metrics.CategoricalAccuracy()]

aimodel/src/subcommands/train_mono.py

@@ -20,6 +20,7 @@ def parse_args():
 	parser.add_argument("--bottleneck", help="The size of the bottleneck [default: 512].", type=int)
 	parser.add_argument("--arch-enc", help="Next of the underlying encoder convnext model to use [default: convnext_xtiny].")
 	parser.add_argument("--arch-dec", help="Next of the underlying decoder convnext model to use [default: convnext_i_xtiny].")
+	parser.add_argument("--learning-rate", help="The initial learning rate. YOU DO NOT USUALLY NEED TO CHANGE THIS. For experimental use only [default: determined automatically].", type=int)
 	
 	
 	return parser
@@ -43,6 +44,8 @@ def run(args):
 		args.arch_enc = "convnext_xtiny"
 	if (not hasattr(args, "arch_dec")) or args.arch_dec == None:
 		args.arch_dec = "convnext_i_xtiny"
+	if (not hasattr(args, "learning_rate")) or args.learning_rate == None:
+		args.learning_rate = None
 	
 	
 	# TODO: Validate args here.
@@ -66,12 +69,13 @@ def run(args):
 	
 	
 	ai = RainfallWaterMono(
-		dir_output=args.output,
-		batch_size=args.batch_size,
+		dir_output		= args.output,
+		batch_size		= args.batch_size,
 		
-		feature_dim=args.bottleneck,
-		model_arch_enc=args.arch_enc,
-		model_arch_dec=args.arch_dec,
+		feature_dim		= args.bottleneck,
+		model_arch_enc	= args.arch_enc,
+		model_arch_dec	= args.arch_dec,
+		learning_rate	= args.learning_rate,
 		
 		metadata = read_metadata(args.input),
 		shape_water_out=[ args.water_size, args.water_size ], # The DESIRED output shape. the actual data will be cropped to match this.