How to solve "No Algorithm Worked" Keras Error? - tensorflow

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.

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.

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.

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)

Answer 4

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.

Answer 5

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

Answer 6

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

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.