From 4d8ce792c93588a76c4bb7b924ec934499b651ed Mon Sep 17 00:00:00 2001 From: Starbeamrainbowlabs Date: Tue, 13 Dec 2022 13:38:27 +0000 Subject: [PATCH] ddeeplabv3+: fix imports/pathing errors --- aimodel/src/deeplabv3_plus_test.py | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/aimodel/src/deeplabv3_plus_test.py b/aimodel/src/deeplabv3_plus_test.py index 99a15e3..639e109 100755 --- a/aimodel/src/deeplabv3_plus_test.py +++ b/aimodel/src/deeplabv3_plus_test.py @@ -88,23 +88,23 @@ def convolution_block( padding="same", use_bias=False, ): - x = layers.Conv2D( + x = tf.keras.layers.Conv2D( num_filters, kernel_size=kernel_size, dilation_rate=dilation_rate, padding="same", use_bias=use_bias, - kernel_initializer=keras.initializers.HeNormal(), + kernel_initializer=tf.keras.initializers.HeNormal(), )(block_input) - x = layers.BatchNormalization()(x) + x = tf.keras.layers.BatchNormalization()(x) return tf.nn.relu(x) def DilatedSpatialPyramidPooling(dspp_input): dims = dspp_input.shape - x = layers.AveragePooling2D(pool_size=(dims[-3], dims[-2]))(dspp_input) + x = tf.keras.layers.AveragePooling2D(pool_size=(dims[-3], dims[-2]))(dspp_input) x = convolution_block(x, kernel_size=1, use_bias=True) - out_pool = layers.UpSampling2D( + out_pool = tf.keras.layers.UpSampling2D( size=(dims[-3] // x.shape[1], dims[-2] // x.shape[2]), interpolation="bilinear", )(x) @@ -113,35 +113,35 @@ def DilatedSpatialPyramidPooling(dspp_input): out_12 = convolution_block(dspp_input, kernel_size=3, dilation_rate=12) out_18 = convolution_block(dspp_input, kernel_size=3, dilation_rate=18) - x = layers.Concatenate(axis=-1)([out_pool, out_1, out_6, out_12, out_18]) + x = tf.keras.layers.Concatenate(axis=-1)([out_pool, out_1, out_6, out_12, out_18]) output = convolution_block(x, kernel_size=1) return output def DeeplabV3Plus(image_size, num_classes): - model_input = keras.Input(shape=(image_size, image_size, 3)) - resnet50 = keras.applications.ResNet50( + model_input = tf.keras.Input(shape=(image_size, image_size, 3)) + resnet50 = tf.keras.applications.ResNet50( weights="imagenet", include_top=False, input_tensor=model_input ) x = resnet50.get_layer("conv4_block6_2_relu").output x = DilatedSpatialPyramidPooling(x) - input_a = layers.UpSampling2D( + input_a = tf.keras.layers.UpSampling2D( size=(image_size // 4 // x.shape[1], image_size // 4 // x.shape[2]), interpolation="bilinear", )(x) input_b = resnet50.get_layer("conv2_block3_2_relu").output input_b = convolution_block(input_b, num_filters=48, kernel_size=1) - x = layers.Concatenate(axis=-1)([input_a, input_b]) + x = tf.keras.layers.Concatenate(axis=-1)([input_a, input_b]) x = convolution_block(x) x = convolution_block(x) - x = layers.UpSampling2D( + x = tf.keras.layers.UpSampling2D( size=(image_size // x.shape[1], image_size // x.shape[2]), interpolation="bilinear", )(x) - model_output = layers.Conv2D(num_classes, kernel_size=(1, 1), padding="same")(x) - return keras.Model(inputs=model_input, outputs=model_output) + model_output = tf.keras.layers.Conv2D(num_classes, kernel_size=(1, 1), padding="same")(x) + return tf.keras.Model(inputs=model_input, outputs=model_output) model = DeeplabV3Plus(image_size=IMAGE_SIZE, num_classes=NUM_CLASSES) @@ -156,9 +156,9 @@ model.summary() # ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ # ██ ██ ██ ██ ██ ██ ██ ████ ██ ██ ████ ██████ -loss = keras.losses.SparseCategoricalCrossentropy(from_logits=True) +loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True) model.compile( - optimizer=keras.optimizers.Adam(learning_rate=0.001), + optimizer=tf.keras.optimizers.Adam(learning_rate=0.001), loss=loss, metrics=["accuracy"], )