Related
I am working on SRGAN model and I created the model and used MSE loss and BCE loss functions to calculate image losses.
If I use BCEWithLogitsLoss, then the code works but theres huge losses. But I tried using BCE loss and it throws CUDA error. Can someone suggest me where did i went wrong and how can I fix the cuda error.
Optimizers are Adam with learning rate 0.0001
Attached the generator and discriminator
class Generator(nn.Module):
def __init__(self, no_of_blocks=16):
super(Generator, self).__init__()
#First layer
self.CV_Block1 = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=9, stride=1, padding=4),
nn.PReLU())
#Residual Blocks
Blocks = []
for _ in range(no_of_blocks):
Blocks.append(Residual_Block(64))
self.Blocks = nn.Sequential(*Blocks)
# Second convolution layer
self.CV_Block3 = nn.Sequential(
nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64, 0.8)
)
# self.Upsample = nn.Sequential(
# UP_Sampling(64, 2),
# UP_Sampling(64, 2)
# )
upsampling = []
for _ in range(2):
upsampling.append(UP_Sampling(64))
self.upsampling = nn.Sequential(*upsampling)
#Final Layer
self.CV_Block_end = nn.Sequential(
nn.Conv2d(64, 3, kernel_size=9, stride=1, padding=4),
nn.Tanh()
)
# self._initialize_weights()
def forward(self, x): #: torch.Tensor
CV1_out = self.CV_Block1(x)
Res_Out = self.Blocks(CV1_out)
CV3_Out = self.CV_Block3(Res_Out)
out = torch.add(CV1_out, CV3_Out)
out = self.upsampling(out)
out = self.CV_Block_end(out)
# out = torch.clamp_(out, 0.0, 1.0)
# gen_out = self.CV_Block_end(x)
return out
class Discriminator(nn.Module):
def __init__(self,input_shape):
super(Discriminator, self).__init__()
# self.input_shape = input_shape
# in_height, in_width = self.input_shape
# patch_h, patch_w = int(in_height / 2 ** 4), int(in_width / 2 ** 4)
# self.output_shape = (1, patch_h, patch_w)
self.features = nn.Sequential(
# input size. (3) x 96 x 96
nn.Conv2d(3, 64, (3, 3), (1, 1), (1, 1), bias=True),
nn.LeakyReLU(0.2, True),
# state size. (64) x 48 x 48
nn.Conv2d(64, 64, (3, 3), (2, 2), (1, 1), bias=False),
nn.BatchNorm2d(64),
nn.LeakyReLU(0.2, True),
nn.Conv2d(64, 128, (3, 3), (1, 1), (1, 1), bias=False),
nn.BatchNorm2d(128),
nn.LeakyReLU(0.2, True),
# state size. (128) x 24 x 24
nn.Conv2d(128, 128, (3, 3), (2, 2), (1, 1), bias=False),
nn.BatchNorm2d(128),
nn.LeakyReLU(0.2, True),
nn.Conv2d(128, 256, (3, 3), (1, 1), (1, 1), bias=False),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2, True),
# state size. (256) x 12 x 12
nn.Conv2d(256, 256, (3, 3), (2, 2), (1, 1), bias=False),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2, True),
nn.Conv2d(256, 512, (3, 3), (1, 1), (1, 1), bias=False),
nn.BatchNorm2d(512),
nn.LeakyReLU(0.2, True),
# state size. (512) x 6 x 6
nn.Conv2d(512, 512, (3, 3), (2, 2), (1, 1), bias=False),
nn.BatchNorm2d(512),
nn.LeakyReLU(0.2, True),
)
self.classifier = nn.Sequential(
nn.Linear(512 * 6 * 6, 1024),
nn.LeakyReLU(0.2, True),
nn.Linear(1024, 1),
nn.Sigmoid(),
)
def forward(self, x):
out = self.features(x)
# out = torch.flatten(out, 1)
# out = self.classifier(out)
return out
Error "device-side assert triggered" triggered inside BCELoss when inputs not in [0..1] (so it not a probabilities).
You got it because remove block classifier block with nn.Sigmoid
# out = self.classifier(out)
There a similar question:
loss.backward() gives RuntimeError: CUDA error: device-side assert triggered
i am new to python and i am trying to create a model that can measure how similar movies are based on the movies description,the steps i followed so far are:
1.turn each movie description into a vector of 100*(maximum number of words possible for a movie description) values using Word2Vec, this results in a 21300-values vector for each movie description.
2.create a deep convolutional autoencoder that tries to compress each vector(and hopefully extract meaning from it).
while the first step was successful and i am still struggling with the autoencoder, here is my code so far:
encoder_input = keras.Input(shape=(21300,), name='sum')
encoded= tf.keras.layers.Reshape((150,142,1),input_shape=(21300,))(encoder_input)
x = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", padding="same",input_shape=(1,128,150,142))(encoded)
x = tf.keras.layers.MaxPooling2D((2, 2), padding="same")(x)
x = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling2D((2, 2), padding="same")(x)#49*25*64
x = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling2D((2, 2), padding="same")(x)#25*13*32
x = tf.keras.layers.Conv2D(16, (3, 3), activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling2D((2, 2), padding="same")(x)
x = tf.keras.layers.Conv2D(8, (3, 3), activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling2D((2, 2), padding="same")(x)
x=tf.keras.layers.Flatten()(x)
encoder_output=keras.layers.Dense(units=90, activation='relu',name='encoder')(x)
x= tf.keras.layers.Reshape((10,9,1),input_shape=(28,))(encoder_output)
# Decoder
decoder_input=tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = tf.keras.layers.UpSampling2D((2, 2))(decoder_input)
x = tf.keras.layers.Conv2D(16, (3, 3), activation='relu')(x)
x = tf.keras.layers.UpSampling2D((2, 2))(x)
x = tf.keras.layers.Conv2D(32, (3, 3), activation='relu')(x)
x = tf.keras.layers.UpSampling2D((2, 2))(x)
x = tf.keras.layers.Conv2D(64, (3, 3), activation='relu')(x)
x = tf.keras.layers.UpSampling2D((2, 2))(x)
x = tf.keras.layers.Conv2D(128, (3, 3), activation='relu')(x)
x = tf.keras.layers.UpSampling2D((2, 2))(x)
decoder_output = keras.layers.Conv2D(1, (3, 3), activation='relu', padding='same')(x)
autoencoder = keras.Model(encoder_input, decoder_output)
opt = tf.keras.optimizers.Adam(learning_rate=0.001, decay=1e-6)
autoencoder = keras.Model(encoder_input, decoder_output, name='autoencoder')
autoencoder.compile(opt, loss='mse')
print("STARTING FITTING")
history = autoencoder.fit(
movies_vector,
movies_vector,
epochs=25,
)
print("ENCODER READY")
#USING THE MIDDLE LAYER
encoder = keras.Model(inputs=autoencoder.input,
outputs=autoencoder.get_layer('encoder').output)
running this code gives me the following error:
required broadcastable shapes [[node mean_squared_error/SquaredDifference (defined at tmp/ipykernel_52/3425712667.py:119) ]] [Op:__inference_train_function_1568]
i have two questions:
1.how can i fix this error?
2.how can i improve my autoencoder so that i can use the compressed vectors to test for movie similarity?
The output of your model is (batch_size, 260, 228, 1), while your targets appear to be (batch_size, 21300). You can solve that problem by either adding a tf.keras.layers.Flatten() layer to the end of your model, or by not flattening your input.
You probably should not be using 2D convolutions, as there is no spatial or temporal correlation between adjacent feature channels in most text embedding. You should be able to safely reshape to (150,142) rather than (150, 142, 1) and use 1D convolution, pooling, and upsampling layers.
i am new to python and i have a dataset that contains movie descriptions and i am trying to create a model that can calculate movie similarity based on these descriptions.
so i started by turning each movie description into a Word2Vec vector where each word has a size 100,since the longest movie description in my dataset has 213 words, each movie description is turned into a vector of size 21300.
now my next step is to reduce the dimensionality of these vectors using a convolutional autoencoder.
it was recommended to me that i turn each 21300-sized vector into a 150 by 142 matrix so i did that, my goal is to compress these matrices from 150 by 142 to 5 by 5 matrix which i will then flatten and use to calculate cosine similarity between different compressed movie vectors.
now here is my faulty code so far:
encoder_input = keras.Input(shape=(21300,), name='sum')
encoded= tf.keras.layers.Reshape((150,142),input_shape=(21300,))(encoder_input)
x = tf.keras.layers.Conv1D(32, 3, activation="relu", padding="same",input_shape=(16,150,142))(encoded)
x = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
x = tf.keras.layers.Conv1D(32, 3, activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
x = tf.keras.layers.Conv1D(16, 3, activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
x = tf.keras.layers.Conv1D(16, 3, activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
x = tf.keras.layers.Conv1D(8, 3, activation="relu", padding="same")(x)
x = tf.keras.layers.MaxPooling1D(2, padding="same")(x)
x=tf.keras.layers.Flatten()(x)
encoder_output=keras.layers.Dense(units=25, activation='relu',name='encoder')(x)
x= tf.keras.layers.Reshape((5,5),input_shape=(25,))(encoder_output)
# Decoder
decoder_input=tf.keras.layers.Conv1D(8, 3, activation='relu', padding='same')(x)
x = tf.keras.layers.UpSampling1D(2)(decoder_input)
x = tf.keras.layers.Conv1D(16, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(16, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(32, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(32, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
#x=tf.keras.layers.Flatten()(x)
decoder_output = keras.layers.Conv1D(1, 3, activation='relu', padding='same')(x)
opt = tf.keras.optimizers.Adam(learning_rate=0.001, decay=1e-6)
autoencoder = keras.Model(encoder_input, decoder_output, name='autoencoder')
autoencoder.compile(opt, loss='mse')
autoencoder.summary()
history = autoencoder.fit(
movies_vector,
movies_vector,
epochs=25
)
print("ENCODER READY")
#USING THE MIDDLE LAYER
encoder = keras.Model(inputs=autoencoder.input,
outputs=autoencoder.get_layer('encoder').output)
running this code produces the following error:
ValueError: Dimensions must be equal, but are 100 and 21300 for '{{node mean_squared_error/SquaredDifference}} = SquaredDifference[T=DT_FLOAT](mean_squared_error/remove_squeezable_dimensions/Squeeze, IteratorGetNext:1)' with input shapes: [?,100], [?,21300].
how can i fix this autoencoder?
I was able to reproduce the error with dummy data. Changing the decoder model as follows will help.
decoder_input=tf.keras.layers.Conv1D(8, 3, activation='relu', padding='same')(x)
x = tf.keras.layers.UpSampling1D(2)(decoder_input)
x = tf.keras.layers.Conv1D(16, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(16, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(32, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x = tf.keras.layers.Conv1D(32, 3, activation='relu')(x)
x = tf.keras.layers.UpSampling1D(2)(x)
x=tf.keras.layers.Conv1D(213, 3, activation='relu', padding='same')(x)
decoder_output = tf.keras.layers.Flatten()(x)
Please find the gist here. Thank you.
I have trained an auto-encoder decoder using Tensorflow Keras
x_train = np.reshape(x_train, (len(x_train), n_row,n_col, 1))
x_test = np.reshape(x_test, (len(x_test), n_row,n_col, 1))
input_img = Input(shape=(n_row,n_col, 1))
x = Convolution2D(16, (10, 10), activation='relu', padding='same')(input_img)
x = MaxPooling2D((5, 5), padding='same')(x)
x = Convolution2D(8, (2, 2), activation='relu', padding='same')(x)
x = MaxPooling2D((3, 3), padding='same')(x)
x = Convolution2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
x = Convolution2D(8, (2, 2), activation='relu', padding='same')(encoded)
x = UpSampling2D((3, 3))(x)
x = Convolution2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((5, 5))(x)
x = Convolution2D(16, (10, 10), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Cropping2D(cropping=((5, 0), (1, 0)), data_format=None)(x)
decoded = Convolution2D(1, (10, 10), activation='sigmoid', padding='same')(x)
autoencoder = Model(inputs=input_img, outputs=decoded)
autoencoder.compile(optimizer='adam', loss='mse')
I can save the total autoencoder model by using
autoencoder.save('...')
How can I save and access to the encoder and to the decoder separately from ?
Since you have saved the autoencoder you can extract the encoder and decoder from the saved autoencoder likewise:
autoencoder= K.models.load_model('your_saved_autoencoder')
encoder = Model(autoencoder.input, autoencoder.layers[-2].output)
decoder_input = Input(shape=(encoding_dim,))
decoder = Model(decoder_input, autoencoder.layers[-1](decoder_input))
You need to assign a unique name for last layer of encoder and decoder then you can reconstruct the encoder and decoder from autoencoder like this:
encoderLayer = autoEncoder.get_layer("encoder")
assert(encoderLayer != None)
decoderLayer = autoEncoder.get_layer("decoder")
assert(decoderLayer != None)
encoder = Keras.Model(
autoEncoder.input,
encoderLayer.output
)
decoder = Keras.Model(
encoderLayer.output,
decoderLayer.output
)
I tried to develop an FCN-16 model in Keras. I initialized the weights with similar FCN-16 model weights.
def FCN8 (nClasses, input_height=256, input_width=256):
## input_height and width must be devisible by 32 because maxpooling with filter size = (2,2) is operated 5 times,
## which makes the input_height and width 2^5 = 32 times smaller
assert input_height % 32 == 0
assert input_width % 32 == 0
IMAGE_ORDERING = "channels_last"
img_input = Input(shape=(input_height, input_width, 3)) ## Assume 224,224,3
## Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_1', data_format=IMAGE_ORDERING)(
img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_2', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool', data_format=IMAGE_ORDERING)(x)
f1 = x
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_2', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool', data_format=IMAGE_ORDERING)(x)
f2 = x
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_2', data_format=IMAGE_ORDERING)(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_3', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool', data_format=IMAGE_ORDERING)(x)
pool3 = x
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_2', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_3', data_format=IMAGE_ORDERING)(x)
pool4 = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool', data_format=IMAGE_ORDERING)(
x) ## (None, 14, 14, 512)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_1', data_format=IMAGE_ORDERING)(pool4)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_2', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_3', data_format=IMAGE_ORDERING)(x)
pool5 = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool', data_format=IMAGE_ORDERING)(
x)
n = 4096
o = (Conv2D(n, (7, 7), activation='relu', padding='same', name="fc6", data_format=IMAGE_ORDERING))(pool5)
conv7 = (Conv2D(n, (1, 1), activation='relu', padding='same', name="fc7", data_format=IMAGE_ORDERING))(o)
conv7 = (Conv2D(nClasses, (1, 1), activation='relu', padding='same', name="conv7_1", data_format=IMAGE_ORDERING))(conv7)
conv7_4 = Conv2DTranspose(nClasses, kernel_size=(2, 2), strides=(2, 2), data_format=IMAGE_ORDERING)(
conv7)
pool411 = (
Conv2D(nClasses, (1, 1), activation='relu', padding='same', name="pool4_11",use_bias=False, data_format=IMAGE_ORDERING))(pool4)
o = Add(name="add")([pool411, conv7_4])
o = Conv2DTranspose(nClasses, kernel_size=(16, 16), strides=(16, 16), use_bias=False, data_format=IMAGE_ORDERING)(o)
o = (Activation('softmax'))(o)
GDI= Model(img_input, o)
GDI.load_weights(Model_Weights_path)
model = Model(img_input, o)
return model
Then I did train, test split and trying to run the model as:
from keras import optimizers
sgd = optimizers.SGD(lr=1E-2, momentum=0.91,decay=5**(-4), nesterov=True)
model.compile(optimizer='sgd',loss='categorical_crossentropy',metrics=['accuracy'],)
hist1 = model.fit(X_train,y_train,validation_data=(X_test,y_test),batch_size=32,epochs=1000,verbose=2)
model.save("/content/drive/My Drive/HCI_prep/new.h5")
But this code is throwing error in the first epoch:
NotFoundError: 2 root error(s) found.
(0) Not found: No algorithm worked!
[[{{node pool4_11_3/Conv2D}}]]
[[loss_4/mul/_629]]
(1) Not found: No algorithm worked!
[[{{node pool4_11_3/Conv2D}}]]
0 successful operations.
0 derived errors ignored.
add the following to your code:
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)
And then restart the python kernel.
Had the same issue.
The padding='same' for MaxPooling didn't work for me.
I changed the color_mode parameter in the train and test generators from 'rgb' to 'grayscale' and then it worked for me.
This worked for me:
import tensorflow as tf
physical_devices = tf.config.list_physical_devices('GPU')
tf.config.experimental.set_memory_growth(physical_devices[0], True)
In my case, this was solved by ending all processes, that still allocated memory on one of the GPUs. Apparently, one of them did not finish (correctly). I did not have to change any code.
My problem was that I called the model with an input_shape of (?,28,28,1) and later called it with (?,28,28,3).
import tensorflow.keras
from tensorflow.keras.models import *
IMAGE_ORDERING = 'channels_last'
# take vgg-16 pretrained model from "https://github.com/fchollet/deep-learning-models" here
pretrained_url = "https://github.com/fchollet/deep-learning-models/" \
"releases/download/v0.1/" \
"vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5"
pretrained = 'imagenet' # 'imagenet' if weights need to be initialized!
"""
Function Name: get_vgg_encoder()
Functionalities: This function defines the VGG encoder part of the FCN network
and initialize this encoder part with VGG pretrained weights.
Parameter:input_height=224, input_width=224, pretrained=pretrained
Returns: final layer of every blocks as f1,f2,f3,f4,f5
"""
def get_vgg_encoder(input_height=224, input_width=224, pretrained=pretrained):
pad = 1
# heights and weights must be divided by 32, for fcn
assert input_height % 32 == 0
assert input_width % 32 == 0
img_input = Input(shape=(input_height, input_width, 3))
# Unlike base paper, stride=1 has not been used here, because
# Keras has default stride=1
x = (ZeroPadding2D((pad, pad), data_format=IMAGE_ORDERING))(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='valid', name='block1_conv1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool', data_format=IMAGE_ORDERING)(x)
f1 = x
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool', data_format=IMAGE_ORDERING)(x)
f2 = x
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2', data_format=IMAGE_ORDERING)(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool', data_format=IMAGE_ORDERING)(x)
x = Dropout(0.5)(x)
f3 = x
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool', data_format=IMAGE_ORDERING)(x)
f4 = x
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2', data_format=IMAGE_ORDERING)(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3', data_format=IMAGE_ORDERING)(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool', data_format=IMAGE_ORDERING)(x)
# x= Dropout(0.5)(x)
f5 = x
# Check if weights are initialised, model is learning!
if pretrained == 'imagenet':
VGG_Weights_path = tensorflow.keras.utils.get_file(
pretrained_url.split("/")[-1], pretrained_url)
Model(img_input, x).load_weights(VGG_Weights_path)
return img_input, [f1, f2, f3, f4, f5]
"""
Function Name: fcn_16()
Functionalities: This function defines the Fully Convolutional part of the FCN network
and adds skip connections to build FCN-16 network
Parameter:n_classes, encoder=get_vgg_encoder, input_height=224,input_width=224
Returns: model
"""
def fcn_16(n_classes, encoder=get_vgg_encoder, input_height=224, input_width=224):
# Take levels from the base model, i.e. vgg
img_input, levels = encoder(input_height=input_height, input_width=input_width)
[f1, f2, f3, f4, f5] = levels
o = f5
# fcn6
o = (Conv2D(4096, (7, 7), activation='relu', padding='same', data_format=IMAGE_ORDERING))(o)
o = Dropout(0.5)(o)
# fc7
o = (Conv2D(4096, (1, 1), activation='relu', padding='same', data_format=IMAGE_ORDERING))(o)
o = Dropout(0.3)(o)
conv7 = (Conv2D(1, (1, 1), activation='relu', padding='same', name="score_sal", data_format=IMAGE_ORDERING))(o)
conv7_4 = Conv2DTranspose(1, kernel_size=(4, 4), strides=(2, 2), padding='same', name="upscore_sal2",
use_bias=False, data_format=IMAGE_ORDERING)(conv7)
pool411 = (
Conv2D(1, (1, 1), activation='relu', padding='same', name="score_pool4", data_format=IMAGE_ORDERING))(f4)
# Add a crop layer
o, o2 = crop(pool411, conv7_4, img_input)
# add skip connection
o = Add()([o, o2])
# 16 x upsample
o = Conv2DTranspose(n_classes, kernel_size=(32, 32), strides=(16, 16), use_bias=False, data_format=IMAGE_ORDERING)(
o)
# crop layer
## Caffe calls crop layer that takes o and img_input as argument, it takes their difference and crops
## But keras takes it as touple, I checked the size diff and put this value manually.
## output dim was 240 , input dim was 224. 240-224=16. so 16/2=8
score = Cropping2D(cropping=((8, 8), (8, 8)), data_format=IMAGE_ORDERING)(o)
o = (Activation('sigmoid'))(score)
model = Model(img_input, o)
model.model_name = "fcn_16"
return model
This error is quite general and basically indicates that "something" went wrong. As, the variety of answers suggest the error can arise from incompatibilities of the implementation with the underlying versions of keras/tensorflow, or the filter sizes are incorrect, or or or...
There is no single solution to this. For me, it also was an input shape issue. Instead of using rgb using grayscale worked as the network expected 1 channel.