How to solve "No Algorithm Worked" Keras Error?

Question

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.

Naldo

See this: medium.com/@adwin596/… – Hypogeous

Thanks, I added the padding=same, and it worked. – Naldo

@Niloy Chakraborty, Can you please confirm if the error is resolved by adding padding=same to maxpooling layers so that we can mention it as an answer for the benefit of the community. Else, can you please share complete traceback so that we can help you.Thanks! – Marje

@Tensorflow Warriors, have a same problem. Building custom UNet. Padding have no difference, for me. I checked link from Geeocode, to sum up i have cudadnn installed on my windows workstation, so it's no help. – Phonic

Thank you, everyone. @TensorflowWarrior I have added the code in an answer section – Naldo

Answer 1

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.

Staten

Cool! Thanks, worked also for me. What is the explanation why this helps? – Slapup

Answer 2

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.

Aubigny

Answer 3

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)

Tamah

This line should be now physical_devices = tf.config.experimental.list_physical_devices('GPU') – Alcoholize

Answer 4

My problem was that I called the model with an input_shape of (?,28,28,1) and later called it with (?,28,28,3).

Chlodwig

I also had this error due to an incorrect input shape – Landgravine

Answer 5

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.

Incognizant

kill the process owning the gpu is a right choice – Moreen

Answer 6

For reference, the full code that fixed the error is as follows:

import tensorflow.keras
from tensorflow.keras.models import *
from tensorflow.keras.layers 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

Naldo

Answer 7

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.

Lamellar

Answer 8

Like @Soren said, this error depends on various situations. It could happen due to VRAM deficiencies, v1, and v2 incompatibilities, shape issues while calling conv or pool, etc.

In my case, this error was arising because I was calling the saved model for inference in Python 3.6 (and TF 2.4.2), while my model was trained in Python 3.10 (and TF 2.8), and some flexible shape operations done in the functional API of Keras/TF was not backward compatible to an older version of TF.

Thus, I would also recommend checking your training and inference environment to make sure there are no bugs or mismatches.

Undoing

Answer 9

It is not the case here, but I got the same error and none of the above solutions works, in fact, it was because on my last convolution, the number of filters was 3 instead of 1 (for a grayscale). And raised (weirdly) the same error.

If you face this error, take a quick look to your last conv.

Heda