I've just started to learn Tensorflow (2.1.0), Keras (2.3.7) with Python 3.7.7.
I want to use VGG16 network to do semantic segmentation with black and white images (200x200x1).
I have used this network, with its original input_size was (224,224,3):
def vgg16_encoder_decoder(input_size = (200,200,1)):
#################################
# Encoder
#################################
inputs = Input(input_size, name = 'input')
conv1 = Conv2D(64, (3, 3), activation = 'relu', padding = 'same', name ='conv1_1')(inputs)
conv1 = Conv2D(64, (3, 3), activation = 'relu', padding = 'same', name ='conv1_2')(conv1)
pool1 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_1')(conv1)
conv2 = Conv2D(128, (3, 3), activation = 'relu', padding = 'same', name ='conv2_1')(pool1)
conv2 = Conv2D(128, (3, 3), activation = 'relu', padding = 'same', name ='conv2_2')(conv2)
pool2 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_2')(conv2)
conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_1')(pool2)
conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_2')(conv3)
conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_3')(conv3)
pool3 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_3')(conv3)
conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_1')(pool3)
conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_2')(conv4)
conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_3')(conv4)
pool4 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_4')(conv4)
conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_1')(pool4)
conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_2')(conv5)
conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_3')(conv5)
pool5 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_5')(conv5)
#################################
# Decoder
#################################
#conv1 = Conv2DTranspose(512, (2, 2), strides = 2, name = 'conv1')(pool5)
upsp1 = UpSampling2D(size = (2,2), name = 'upsp1')(pool5)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_1')(upsp1)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_2')(conv6)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_3')(conv6)
upsp2 = UpSampling2D(size = (2,2), name = 'upsp2')(conv6)
conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_1')(upsp2)
conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_2')(conv7)
conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_3')(conv7)
upsp3 = UpSampling2D(size = (2,2), name = 'upsp3')(conv7)
conv8 = Conv2D(256, 3, activation = 'relu', padding = 'same', name = 'conv8_1')(upsp3)
conv8 = Conv2D(256, 3, activation = 'relu', padding = 'same', name = 'conv8_2')(conv8)
conv8 = Conv2D(256, 3, activation = 'relu', padding = 'same', name = 'conv8_3')(conv8)
upsp4 = UpSampling2D(size = (2,2), name = 'upsp4')(conv8)
conv9 = Conv2D(128, 3, activation = 'relu', padding = 'same', name = 'conv9_1')(upsp4)
conv9 = Conv2D(128, 3, activation = 'relu', padding = 'same', name = 'conv9_2')(conv9)
upsp5 = UpSampling2D(size = (2,2), name = 'upsp5')(conv9)
conv10 = Conv2D(64, 3, activation = 'relu', padding = 'same', name = 'conv10_1')(upsp5)
conv10 = Conv2D(64, 3, activation = 'relu', padding = 'same', name = 'conv10_2')(conv10)
conv11 = Conv2D(3, 3, activation = 'relu', padding = 'same', name = 'conv11')(conv10)
model = Model(inputs = inputs, outputs = conv11, name = 'vgg-16_encoder_decoder')
return model
Model summary:
Model: "vgg-16_encoder_decoder"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (InputLayer) (None, 200, 200, 1) 0
_________________________________________________________________
conv1_1 (Conv2D) (None, 200, 200, 64) 640
_________________________________________________________________
conv1_2 (Conv2D) (None, 200, 200, 64) 36928
_________________________________________________________________
pool_1 (MaxPooling2D) (None, 100, 100, 64) 0
_________________________________________________________________
conv2_1 (Conv2D) (None, 100, 100, 128) 73856
_________________________________________________________________
conv2_2 (Conv2D) (None, 100, 100, 128) 147584
_________________________________________________________________
pool_2 (MaxPooling2D) (None, 50, 50, 128) 0
_________________________________________________________________
conv3_1 (Conv2D) (None, 50, 50, 256) 295168
_________________________________________________________________
conv3_2 (Conv2D) (None, 50, 50, 256) 590080
_________________________________________________________________
conv3_3 (Conv2D) (None, 50, 50, 256) 590080
_________________________________________________________________
pool_3 (MaxPooling2D) (None, 25, 25, 256) 0
_________________________________________________________________
conv4_1 (Conv2D) (None, 25, 25, 512) 1180160
_________________________________________________________________
conv4_2 (Conv2D) (None, 25, 25, 512) 2359808
_________________________________________________________________
conv4_3 (Conv2D) (None, 25, 25, 512) 2359808
_________________________________________________________________
pool_4 (MaxPooling2D) (None, 12, 12, 512) 0
_________________________________________________________________
conv5_1 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv5_2 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv5_3 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
pool_5 (MaxPooling2D) (None, 6, 6, 512) 0
_________________________________________________________________
upsp1 (UpSampling2D) (None, 12, 12, 512) 0
_________________________________________________________________
conv6_1 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv6_2 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv6_3 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
upsp2 (UpSampling2D) (None, 24, 24, 512) 0
_________________________________________________________________
conv7_1 (Conv2D) (None, 24, 24, 512) 2359808
_________________________________________________________________
conv7_2 (Conv2D) (None, 24, 24, 512) 2359808
_________________________________________________________________
conv7_3 (Conv2D) (None, 24, 24, 512) 2359808
_________________________________________________________________
upsp3 (UpSampling2D) (None, 48, 48, 512) 0
_________________________________________________________________
conv8_1 (Conv2D) (None, 48, 48, 256) 1179904
_________________________________________________________________
conv8_2 (Conv2D) (None, 48, 48, 256) 590080
_________________________________________________________________
conv8_3 (Conv2D) (None, 48, 48, 256) 590080
_________________________________________________________________
upsp4 (UpSampling2D) (None, 96, 96, 256) 0
_________________________________________________________________
conv9_1 (Conv2D) (None, 96, 96, 128) 295040
_________________________________________________________________
conv9_2 (Conv2D) (None, 96, 96, 128) 147584
_________________________________________________________________
upsp5 (UpSampling2D) (None, 192, 192, 128) 0
_________________________________________________________________
conv10_1 (Conv2D) (None, 192, 192, 64) 73792
_________________________________________________________________
conv10_2 (Conv2D) (None, 192, 192, 64) 36928
_________________________________________________________________
conv11 (Conv2D) (None, 192, 192, 3) 1731
=================================================================
Total params: 31,787,523
Trainable params: 31,787,523
Non-trainable params: 0
_________________________________________________________________
The last convolutional layer returns a shape of (192, 192, 3) but I need to return an image with shape (200, 200, 1).
I think I can change the last convolutional layer with this one to get a 1 channel image:
conv11 = Conv2D(1, 3, activation = 'relu', padding = 'same', name = 'conv11')(conv10)
But I don't know if this is correct because I've been reading about VGG16 network and it is for 3 channels images.
Can I use VGG16 for one channel images?
What you read about VGG being for three channel (RGB) images applies only to the pre-trained model, which is trained on the ImageNet dataset and contains only color images. Since you are not using the pre-trained model, you are not bound by this limitation.
So you can use one, three, or any number of inputs or output channels.
Related
Good evening everyone,
I have 5 classes and each one has 2000 images, I built 2 Models with different model names and that's my model code
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(32, (3, 3), activation='relu',
input_shape=(150, 150, 3)),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(5, activation=tf.nn.softmax)
], name="Model1")
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(train_images, train_labels,
batch_size=128, epochs=30, validation_split=0.2)
model.save('f3_1st_model_seg.h5')
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(32, (3, 3), activation='relu',
input_shape=(150, 150, 3)),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(5, activation=tf.nn.softmax)
], name="Model2")
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(train_images, train_labels,
batch_size=128, epochs=30, validation_split=0.2)
model.save('f3_2nd_model_seg.h5')
then I used this code to merge the 2 models
input_shape = [150, 150, 3]
model = keras.models.load_model('1st_model_seg.h5')
model.summary()
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 148, 148, 32) 896
max_pooling2d (MaxPooling2D (None, 74, 74, 32) 0
)
conv2d_1 (Conv2D) (None, 72, 72, 32) 9248
max_pooling2d_1 (MaxPooling (None, 36, 36, 32) 0
2D)
conv2d_2 (Conv2D) (None, 34, 34, 64) 18496
max_pooling2d_2 (MaxPooling (None, 17, 17, 64) 0
2D)
conv2d_3 (Conv2D) (None, 15, 15, 128) 73856
max_pooling2d_3 (MaxPooling (None, 7, 7, 128) 0
2D)
flatten (Flatten) (None, 6272) 0
dense (Dense) (None, 5) 31365
=================================================================
Total params: 133,861
Trainable params: 133,861
Non-trainable params: 0
model2 = keras.models.load_model('2nd_model_seg.h5')
model2.summary()
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 148, 148, 32) 896
max_pooling2d (MaxPooling2D (None, 74, 74, 32) 0
)
conv2d_1 (Conv2D) (None, 72, 72, 32) 9248
max_pooling2d_1 (MaxPooling (None, 36, 36, 32) 0
2D)
conv2d_2 (Conv2D) (None, 34, 34, 64) 18496
max_pooling2d_2 (MaxPooling (None, 17, 17, 64) 0
2D)
conv2d_3 (Conv2D) (None, 15, 15, 128) 73856
max_pooling2d_3 (MaxPooling (None, 7, 7, 128) 0
2D)
flatten (Flatten) (None, 6272) 0
dense (Dense) (None, 5) 31365
=================================================================
Total params: 133,861
Trainable params: 133,861
Non-trainable params: 0
def concat_horizontal(models, input_shape):
models_count = len(models)
hidden = []
input = tf.keras.layers.Input(shape=input_shape)
for i in range(models_count):
hidden.append(models[i](input))
output = tf.keras.layers.concatenate(hidden)
model = tf.keras.Model(inputs=input, outputs=output)
return model
new_model = concat_horizontal(
[model, model2], (input_shape))
new_model.save('f1_1st_merged_seg.h5')
new_model.summary()
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 150, 150, 3 0 []
)]
model1 (Sequential) (None, 5) 133861 ['input_1[0][0]']
model2 (Sequential) (None, 5) 133861 ['input_1[0][0]']
concatenate (Concatenate) (None, 10) 0 ['model1[0][0]',
'model2[0][0]']
==================================================================================================
Total params: 267,722
Trainable params: 267,722
Non-trainable params: 0
so after I tested the merged model I found some images getting classes 7 and 9 although I have only 5 classes and that's my code for prediction
class_names = ['A', 'B', 'C', D', 'E']
for img in os.listdir(path):
# predicting images
img2 = tf.keras.preprocessing.image.load_img(
os.path.join(path, img), target_size=(150, 150))
x = tf.keras.preprocessing.image.img_to_array(img2)
x = np.expand_dims(x, axis=0)
images = np.vstack([x])
classes = np.argmax(model.predict(images), axis=-1)
y_out = class_names[classes[0]]
I got this error
y_out = class_names[classes[0]]
IndexError: list index out of range
for this case it could have been done even by sequential method, look you are trying to concatenate two output layers with 5 columns; so it would lead into increase classes from 5 to 10; try out to define these two models up to output layer (the flatten layer as the last layer defined for both these models) and then define final model with input layer, these two models, and concatenate layer and then the output layer with five units and activation;
so remove output layer
tf.keras.layers.Dense(5, activation=tf.nn.softmax)
from those two models, and implement it just as one layer after the output layer you have defined here
def concat_horizontal(models, input_shape):
models_count = len(models)
hidden = []
input = tf.keras.layers.Input(shape=input_shape)
for i in range(models_count):
hidden.append(models[i](input))
output = tf.keras.layers.concatenate(hidden)
output = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(output)
model = tf.keras.Model(inputs=input, outputs=output)
return model
But notice it would be better to define branch models based on functional API method for these cases
I want to create an autoencodre i build this architecture it works but i want to know if it is an autoencoder architecture
Encoder
layer = layers.Conv2D(16, (3, 3), activation="relu", padding="same",data_format = 'channels_first')(input)
layer = layers.MaxPooling2D((2, 2), padding="same",data_format = 'channels_first')(layer)
layer = layers.Conv2D(32, (3, 3), activation="relu", padding="same",data_format = 'channels_first')(layer)
layer = layers.MaxPooling2D((2, 2), padding="same",data_format = 'channels_first')(layer)
## Decoder
layer = layers.Conv2DTranspose(16, (3, 3), strides=2, activation="relu", padding="same",data_format = 'channels_first')(layer)
layer = layers.UpSampling2D((2,2))(layer)
layer = layers.Conv2DTranspose(32, (3, 3), strides=2, activation="relu", padding="same",data_format = 'channels_first')(layer)
layer = layers.UpSampling2D((2,2))(layer)
#layer = layers.UpSampling2D((2,2))(layer)
layer = layers.Flatten()(layer)
dense = layers.Dense(784, activation="sigmoid")
output = dense(layer)
There are some problems in your code:
You need an input layer to your model if you are using functional:
input = layers.Input(shape=(3, 192, 192))
In an autoencoder, the output of your model needs to have the same dimensions as the input. However, in your model your output is a dense vector (1D), while your input is obviously at least 2D (or 3D if you have channels, like in images).
You have specified the argument data_format = 'channels_first' which means that your input tensor has the channel dimension in the position 0. For example, if your input is an rgb image, it has shape (color_channel, width, height), instead of the more common (width, heigth, color_channel). That is ok, but 1) Make sure your images have channels first and 2) You need to pass the same argument on your upsampling layers.
With a couple of changes, the model looks like this:
## Encoder
input = layers.Input(shape=(3, 192, 192))
layer = layers.Conv2D(16, (3, 3), activation="relu", padding="same",data_format = 'channels_first')(input)
layer = layers.MaxPooling2D((2, 2), padding="same",data_format = 'channels_first')(layer)
layer = layers.Conv2D(32, (3, 3), activation="relu", padding="same",data_format = 'channels_first')(layer)
layer = layers.MaxPooling2D((2, 2), padding="same",data_format = 'channels_first')(layer)
## Decoder
layer = layers.Conv2DTranspose(16, (3, 3), strides=1, activation="relu", padding="same",data_format = 'channels_first')(layer)
layer = layers.UpSampling2D((2,2), data_format='channels_first')(layer)
layer = layers.Conv2DTranspose(32, (3, 3), strides=1, activation="relu", padding="same",data_format = 'channels_first')(layer)
layer = layers.UpSampling2D((2,2), data_format='channels_first')(layer)
output = layers.Conv2DTranspose(3, (3, 3), strides=1, activation="relu", padding="same",data_format = 'channels_first')(layer)
model = tf.keras.Model(inputs=input, outputs=output)
model.summary()
Model: "model_8"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_10 (InputLayer) [(None, 3, 192, 192)] 0
_________________________________________________________________
conv2d_19 (Conv2D) (None, 16, 192, 192) 448
_________________________________________________________________
max_pooling2d_18 (MaxPooling (None, 16, 96, 96) 0
_________________________________________________________________
conv2d_20 (Conv2D) (None, 32, 96, 96) 4640
_________________________________________________________________
max_pooling2d_19 (MaxPooling (None, 32, 48, 48) 0
_________________________________________________________________
conv2d_transpose_19 (Conv2DT (None, 16, 48, 48) 4624
_________________________________________________________________
up_sampling2d_17 (UpSampling (None, 16, 96, 96) 0
_________________________________________________________________
conv2d_transpose_20 (Conv2DT (None, 32, 96, 96) 4640
_________________________________________________________________
up_sampling2d_18 (UpSampling (None, 32, 192, 192) 0
_________________________________________________________________
conv2d_transpose_21 (Conv2DT (None, 3, 192, 192) 867
=================================================================
Total params: 15,219
Trainable params: 15,219
Non-trainable params: 0
I'm trying to apply Conv1D layers for a classification model which has a numeric dataset. The neural network of my model is as follows:
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv1D(8,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu',input_shape = (14999,7)))
model.add(tf.keras.layers.Conv1D(16,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.MaxPooling1D(2))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Conv1D(32,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.Conv1D(64,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.MaxPooling1D(2))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Conv1D(128,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.Conv1D(256,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu'))
model.add(tf.keras.layers.MaxPooling1D(2))
model.add(tf.keras.layers.Dropout(0.2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(512,activation = 'relu'))
model.add(tf.keras.layers.Dense(128,activation = 'relu'))
model.add(tf.keras.layers.Dense(32,activation = 'relu'))
model.add(tf.keras.layers.Dense(3, activation = 'softmax'))
And the model's input shape is (14999, 7).
model.summary() gives the following output
Model: "sequential_8"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d_24 (Conv1D) (None, 14997, 8) 176
_________________________________________________________________
conv1d_25 (Conv1D) (None, 14995, 16) 400
_________________________________________________________________
max_pooling1d_10 (MaxPooling (None, 7497, 16) 0
_________________________________________________________________
dropout_9 (Dropout) (None, 7497, 16) 0
_________________________________________________________________
conv1d_26 (Conv1D) (None, 7495, 32) 1568
_________________________________________________________________
conv1d_27 (Conv1D) (None, 7493, 64) 6208
_________________________________________________________________
max_pooling1d_11 (MaxPooling (None, 3746, 64) 0
_________________________________________________________________
dropout_10 (Dropout) (None, 3746, 64) 0
_________________________________________________________________
conv1d_28 (Conv1D) (None, 3744, 128) 24704
_________________________________________________________________
conv1d_29 (Conv1D) (None, 3742, 256) 98560
_________________________________________________________________
max_pooling1d_12 (MaxPooling (None, 1871, 256) 0
_________________________________________________________________
dropout_11 (Dropout) (None, 1871, 256) 0
_________________________________________________________________
flatten_3 (Flatten) (None, 478976) 0
_________________________________________________________________
dense_14 (Dense) (None, 512) 245236224
_________________________________________________________________
dense_15 (Dense) (None, 128) 65664
_________________________________________________________________
dense_16 (Dense) (None, 32) 4128
_________________________________________________________________
dense_17 (Dense) (None, 3) 99
=================================================================
Total params: 245,437,731
Trainable params: 245,437,731
Non-trainable params: 0
The code for model fitting is:
model.compile(loss = 'sparse_categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
history = model.fit(xtrain_scaled, ytrain_scaled, epochs = 30, batch_size = 5, validation_data = (xval_scaled, yval_scaled))
While executing, I'm facing the following error:
ValueError: Input 0 is incompatible with layer model: expected shape=(None, 14999, 7), found shape=(None, 7)
Could anyone help to sort out this issue?
TL;DR:
Change
model.add(tf.keras.layers.Conv1D(8,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu',input_shape = (14999,7)))
to
model.add(tf.keras.layers.Conv1D(8,kernel_size = 3, strides = 1,padding = 'valid', activation = 'relu',input_shape = (7)))
Full answer:
Assumption: I am guessing the reason you chose to write 14999 in the input shape is because that's your batch size / total size of training data
Problem with this:
Tensorflow assumes the input shape does not include the batch size
By specifying a 2D input_shape you're making Tensorflow expect a 3D input of shape (Batch_size, 14999, 7). But your input is clearly of size (Batch_size, 7)
Solution:
Change the shape from (14999, 7) to just (7)
TF will now be expecting the same shape that you are providing
PS: Don't be worried about informing your model of how many training examples you have in the dataset. TF Keras works with the assumption it can be shown unlimited training examples.
I've just started to learn Tensorflow (2.1.0), Keras (2.3.7) with Python 3.7.7.
I'm trying an encoder-decoder network using VGG16.
I need to Upsample a layer from (12, 12, ...) to (25, 25, ...) to make conv7_1 has the same shape as conv4_3 layer. The layer with the 'problem' is upsp2:
conv4_3 (Conv2D) (None, 25, 25, 512) 2359808
_________________________________________________________________
pool_4 (MaxPooling2D) (None, 12, 12, 512) 0
_________________________________________________________________
conv5_1 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv5_2 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv5_3 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
pool_5 (MaxPooling2D) (None, 6, 6, 512) 0
_________________________________________________________________
upsp1 (UpSampling2D) (None, 12, 12, 512) 0
_________________________________________________________________
conv6_1 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv6_2 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
conv6_3 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
upsp2 (UpSampling2D) (None, 24, 24, 512) 0
_________________________________________________________________
conv7_1 (Conv2D) (None, 24, 24, 512) 2359808
I have tried this:
#################################
# Decoder
#################################
#conv1 = Conv2DTranspose(512, (2, 2), strides = 2, name = 'conv1')(pool5)
upsp1 = UpSampling2D(size = (2,2), name = 'upsp1')(pool5)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_1')(upsp1)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_2')(conv6)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_3')(conv6)
zero1 = ZeroPadding2D(padding = (1,1), data_format = 'channels_last', name='zero1')(conv6)
upsp2 = UpSampling2D(size = (2,2), name = 'upsp2')(zero1)
But I get that shape (12, 12, ...) gets into (14, 14, ...) at zero1 layer:
conv6_3 (Conv2D) (None, 12, 12, 512) 2359808
_________________________________________________________________
zero1 (ZeroPadding2D) (None, 14, 14, 512) 0
_________________________________________________________________
upsp2 (UpSampling2D) (None, 28, 28, 512) 0
_________________________________________________________________
How can I upsample (12,12,512) to (25,25,512)?
I did it using padding as a tuple of 2 tuples of 2 ints: interpreted as ((top_pad, bottom_pad), (left_pad, right_pad)). And setting ZeroPadding2D at the end of convolution 7 layer:
#################################
# Decoder
#################################
#conv1 = Conv2DTranspose(512, (2, 2), strides = 2, name = 'conv1')(pool5)
upsp1 = UpSampling2D(size = (2,2), name = 'upsp1')(pool5)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_1')(upsp1)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_2')(conv6)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_3')(conv6)
upsp2 = UpSampling2D(size = (2,2), name = 'upsp2')(conv6)
conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_1')(upsp2)
conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_2')(conv7)
conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_3')(conv7)
zero1 = ZeroPadding2D(padding = ((1, 0), (1, 0)), data_format = 'channels_last', name='zero1')(conv7)
I am trying to design a CNN that can do pixel wise segmentation of cell images. Such as these:
With segmentation masks such as this (except more than one segmentation mask for each raw image, eg: interior of cell, border of cell, background):
I have mostly copied the U-net design from here: https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/
However even 10 annotated images (over 300 cells) I still get quite bad dice coefficient scores and not great predictions. According to the U-Net paper this number of annotated cells should be sufficient for a good prediction.
This is the code for the model I am using.
def get_unet():
inputs = Input((img_rows, img_cols, 1))
conv1 = Conv2D(16, window_size, activation='relu', padding='same')(inputs)
conv1 = Conv2D(16, window_size, activation='relu', padding='same')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Conv2D(64, window_size, activation='relu', padding='same')(pool1)
conv2 = Conv2D(64, window_size, activation='relu', padding='same')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Conv2D(128, window_size, activation='relu', padding='same')(pool2)
conv3 = Conv2D(128, window_size, activation='relu', padding='same')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Conv2D(128, window_size, activation='relu', padding='same')(pool3)
conv4 = Conv2D(128, window_size, activation='relu', padding='same')(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
conv5 = Conv2D(512, window_size, activation='relu', padding='same')(pool4)
conv5 = Conv2D(512, window_size, activation='relu', padding='same')(conv5)
up6 = concatenate([Conv2DTranspose(512, (2, 2), strides=(2, 2), padding='same')(conv5), conv4], axis=3)
conv6 = Conv2D(128, window_size, activation='relu', padding='same')(up6)
conv6 = Conv2D(128, window_size, activation='relu', padding='same')(conv6)
up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv6), conv3], axis=3)
conv7 = Conv2D(128, window_size, activation='relu', padding='same')(up7)
conv7 = Conv2D(128, window_size, activation='relu', padding='same')(conv7)
up8 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv7), conv2], axis=3)
conv8 = Conv2D(64, window_size, activation='relu', padding='same')(up8)
conv8 = Conv2D(64, window_size, activation='relu', padding='same')(conv8)
up9 = concatenate([Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(conv8), conv1], axis=3)
conv9 = Conv2D(16, window_size, activation='relu', padding='same')(up9)
conv9 = Conv2D(16, window_size, activation='relu', padding='same')(conv9)
conv10 = Conv2D(f_num, (1, 1), activation='softmax')(conv9) # change to N,(1,1) for more classes and softmax
model = Model(inputs=[inputs], outputs=[conv10])
model.compile(optimizer=Adam(lr=1e-5), loss=dice_coef_loss, metrics=[dice_coef])
return model`
I have tried many different hyper-parameters for the model all with no success. Dice scores hover around 0.25 and my loss barely decreases between epochs.
I feel I am doing something fundamentally wrong here. Any suggestions?
EDIT: Sigmoid activation improves dice score from 0.25 to 0.33 (again however 1 epoch reaches this score and subsequent epochs only improve very slightly from 0.33 to 0.331 etc)
dice_coef_loss is defined as below
smooth = 1.
def dice_coef(y_true, y_pred):
y_true_f = K.flatten(y_true)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
def dice_coef_loss(y_true, y_pred):
return -dice_coef(y_true, y_pred)
Also in case it's useful the model.summary output:
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) (None, 64, 64, 1) 0
_________________________________________________________________
conv2d_20 (Conv2D) (None, 64, 64, 16) 32
_________________________________________________________________
conv2d_21 (Conv2D) (None, 64, 64, 16) 272
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 32, 32, 16) 0
_________________________________________________________________
conv2d_22 (Conv2D) (None, 32, 32, 64) 1088
_________________________________________________________________
conv2d_23 (Conv2D) (None, 32, 32, 64) 4160
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 16, 16, 64) 0
_________________________________________________________________
conv2d_24 (Conv2D) (None, 16, 16, 128) 8320
_________________________________________________________________
conv2d_25 (Conv2D) (None, 16, 16, 128) 16512
_________________________________________________________________
max_pooling2d_7 (MaxPooling2 (None, 8, 8, 128) 0
_________________________________________________________________
conv2d_26 (Conv2D) (None, 8, 8, 128) 16512
_________________________________________________________________
conv2d_27 (Conv2D) (None, 8, 8, 128) 16512
_________________________________________________________________
max_pooling2d_8 (MaxPooling2 (None, 4, 4, 128) 0
_________________________________________________________________
conv2d_28 (Conv2D) (None, 4, 4, 512) 66048
_________________________________________________________________
conv2d_29 (Conv2D) (None, 4, 4, 512) 262656
_________________________________________________________________
conv2d_transpose_5 (Conv2DTr (None, 8, 8, 512) 1049088
_________________________________________________________________
concatenate_5 (Concatenate) (None, 8, 8, 640) 0
_________________________________________________________________
conv2d_30 (Conv2D) (None, 8, 8, 128) 82048
_________________________________________________________________
conv2d_31 (Conv2D) (None, 8, 8, 128) 16512
_________________________________________________________________
conv2d_transpose_6 (Conv2DTr (None, 16, 16, 128) 65664
_________________________________________________________________
concatenate_6 (Concatenate) (None, 16, 16, 256) 0
_________________________________________________________________
conv2d_32 (Conv2D) (None, 16, 16, 128) 32896
_________________________________________________________________
conv2d_33 (Conv2D) (None, 16, 16, 128) 16512
_________________________________________________________________
conv2d_transpose_7 (Conv2DTr (None, 32, 32, 128) 65664
_________________________________________________________________
concatenate_7 (Concatenate) (None, 32, 32, 192) 0
_________________________________________________________________
conv2d_34 (Conv2D) (None, 32, 32, 64) 12352
_________________________________________________________________
conv2d_35 (Conv2D) (None, 32, 32, 64) 4160
_________________________________________________________________
conv2d_transpose_8 (Conv2DTr (None, 64, 64, 64) 16448
_________________________________________________________________
concatenate_8 (Concatenate) (None, 64, 64, 80) 0
_________________________________________________________________
conv2d_36 (Conv2D) (None, 64, 64, 16) 1296
_________________________________________________________________
conv2d_37 (Conv2D) (None, 64, 64, 16) 272
_________________________________________________________________
conv2d_38 (Conv2D) (None, 64, 64, 4) 68
=================================================================
Total params: 1,755,092.0
Trainable params: 1,755,092.0
Non-trainable params: 0.0