ValueError: No gradients provided for any variable: ['conv2d/kernel:0', 'conv2d/bias:0', 'conv2d_1/kernel:0', 'conv2d_1/bias:0',

Question

System information Colab tensorflow 2.2.0

Describe the current behavior: I faced this error when i tried to solve my own data issues, which is multiple label semantic segmentations.

Below is the code

import tensorflow as tf
import tensorflow.keras.backend as K

IMG_WIDTH = 512
IMG_HEIGHT = 512
IMG_CHANNELS = 3

# batch_shape=(512,512,3)
# inputs = Input(batch_shape=(4, 512, 512, 3))
#Build the model
inputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))
#s = tf.keras.layers.Lambda(lambda x: x / 255)(inputs)

#Contraction path
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(inputs)
c1 = tf.keras.layers.Dropout(0.1)(c1)
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c1)
p1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)

c2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p1)
c2 = tf.keras.layers.Dropout(0.1)(c2)
c2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c2)
p2 = tf.keras.layers.MaxPooling2D((2, 2))(c2)

c3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p2)
c3 = tf.keras.layers.Dropout(0.2)(c3)
c3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c3)
p3 = tf.keras.layers.MaxPooling2D((2, 2))(c3)

c4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p3)
c4 = tf.keras.layers.Dropout(0.2)(c4)
c4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c4)
p4 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(c4)

c5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p4)
c5 = tf.keras.layers.Dropout(0.3)(c5)
c5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c5)

#Expansive path 
u6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(c5)
u6 = tf.keras.layers.concatenate([u6, c4])
c6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u6)
c6 = tf.keras.layers.Dropout(0.2)(c6)
c6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c6)

u7 = tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(c6)
u7 = tf.keras.layers.concatenate([u7, c3])
c7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u7)
c7 = tf.keras.layers.Dropout(0.2)(c7)
c7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c7)

u8 = tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(c7)
u8 = tf.keras.layers.concatenate([u8, c2])
c8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u8)
c8 = tf.keras.layers.Dropout(0.1)(c8)
c8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c8)

u9 = tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same')(c8)
u9 = tf.keras.layers.concatenate([u9, c1], axis=3)
c9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u9)
c9 = tf.keras.layers.Dropout(0.1)(c9)
c9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c9)

outputs = tf.keras.layers.Conv2D(6, (1, 1), activation='softmax')(c9)

model = tf.keras.Model(inputs=[inputs], outputs=[outputs])

# define optomizer
optim = tf.keras.optimizers.Adam()

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*y_true_f) + K.sum(y_pred_f*y_pred_f) + smooth)


def dice_coef_loss(y_true, y_pred):
    return 1.-dice_coef(y_true, y_pred)

smooth = 1.
loss= tf.keras.losses.CategoricalCrossentropy()

model.compile(optim, loss, metrics=[dice_coef,'accuracy'])

#model.compile(optim, metrics, loss)
model.summary()

#SET UP FOR DATA TRAINING

BATCH_SIZE = 4
CLASSES = ['0', '1','2','3','4','5']
LR = 0.0001
EPOCHS = 40
n_classes = len(CLASSES)

# Dataset for train images
train_dataset = Dataset(
    x_train_dir, 
    y_train_dir, 
    classes=CLASSES, 
    augmentation=get_training_augmentation(),
    preprocessing=get_preprocessing(),
    with_shape_assert= True,
)

# Dataset for validation images
valid_dataset = Dataset(
    x_valid_dir, 
    y_valid_dir, 
    classes=CLASSES, 
    augmentation=get_validation_augmentation(),
    preprocessing=get_preprocessing(),
    with_shape_assert= True,
)

train_dataloader = Dataloader(train_dataset, batch_size=BATCH_SIZE, shuffle=True)
valid_dataloader = Dataloader(valid_dataset, batch_size=4, shuffle=False)

# check shapes for errors
assert train_dataloader[0][0].shape == (BATCH_SIZE, 512, 512, 3)
assert train_dataloader[0][1].shape == (BATCH_SIZE, 512, 512, n_classes)

# define callbacks for learning rate scheduling and best checkpoints saving
callbacks = [
    tf.keras.callbacks.ModelCheckpoint('./best_model.h5', save_weights_only=False, save_best_only=True, mode='min'),
    tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)
]
results_2704 = model.fit(
    train_dataloader, 
    steps_per_epoch=len(train_dataloader), 
    epochs=EPOCHS, 
    validation_data=valid_dataloader, 
    callbacks=callbacks, 
    validation_steps=len(valid_dataloader),verbose=1
)

This will give the error:

ValueError: No gradients provided for any variable: ['conv2d/kernel:0', 'conv2d/bias:0', 'conv2d_1/kernel:0', 'conv2d_1/bias:0', 'conv2d_2/kernel:0', 'conv2d_2/bias:0', 'conv2d_3/kernel:0', 'conv2d_3/bias:0', 'conv2d_4/kernel:0', 'conv2d_4/bias:0', 'conv2d_5/kernel:0', 'conv2d_5/bias:0', 'conv2d_6/kernel:0', 'conv2d_6/bias:0', 'conv2d_7/kernel:0', 'conv2d_7/bias:0', 'conv2d_8/kernel:0', 'conv2d_8/bias:0', 'conv2d_9/kernel:0', 'conv2d_9/bias:0', 'conv2d_transpose/kernel:0', 'conv2d_transpose/bias:0', 'conv2d_10/kernel:0', 'conv2d_10/bias:0', 'conv2d_11/kernel:0', 'conv2d_11/bias:0', 'conv2d_transpose_1/kernel:0', 'conv2d_transpose_1/bias:0', 'conv2d_12/kernel:0', 'conv2d_12/bias:0', 'conv2d_13/kernel:0', 'conv2d_13/bias:0', 'conv2d_transpose_2/kernel:0', 'conv2d_transpose_2/bias:0', 'conv2d_14/kernel:0', 'conv2d_14/bias:0', 'conv2d_15/kernel:0', 'conv2d_15/bias:0', 'conv2d_transpose_3/kernel:0', 'conv2d_transpose_3/bias:0', 'conv2d_16/kernel:0', 'conv2d_16/bias:0', 'conv2d_17/kernel:0', 'conv2d_17/bias:0', 'conv2d_18/kernel:0', 'conv2d_18/bias:0'].

I know it is maybe due to the dead gradients and I have been trying to solve this problem while also posted on Tensorflow github for a month but till now i still do not figure out the solution. So I post here to seek for the help of other Tensorflow experts who may give me some hints while waiting for updating from Tensorflow support person. I searched around and I knew that using tf.GradientTape() may help solve the issue but I myself still could not figure out the right way.

Really looking forward to any advise. Thank you very much

Answer 1

You get this error when you pass only the training data and missed to pass the labels in model.fit(). I was able to recreate your error using below code. You can download the dataset I am using in the program from here.

Code to recreate the issue -

%tensorflow_version 2.x
# MLP for Pima Indians Dataset saved to single file
import numpy as np
from numpy import loadtxt
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# load pima indians dataset
dataset = np.loadtxt("/content/pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# define model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Model Summary
#model.summary()

# Fit the model
model.fit(X, epochs=150, batch_size=10, verbose=0)

Output -

2.2.0
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-4-7ddca8f2992e> in <module>()
     28 
     29 # Fit the model
---> 30 model.fit(X, epochs=150, batch_size=10, verbose=0)

10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    966           except Exception as e:  # pylint:disable=broad-except
    967             if hasattr(e, "ag_error_metadata"):
--> 968               raise e.ag_error_metadata.to_exception(e)
    969             else:
    970               raise

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function  *
        outputs = self.distribute_strategy.run(
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:541 train_step  **
        self.trainable_variables)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1804 _minimize
        trainable_variables))
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:521 _aggregate_gradients
        filtered_grads_and_vars = _filter_grads(grads_and_vars)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:1219 _filter_grads
        ([v.name for _, v in grads_and_vars],))

    ValueError: No gradients provided for any variable: ['dense_5/kernel:0', 'dense_5/bias:0', 'dense_6/kernel:0', 'dense_6/bias:0', 'dense_7/kernel:0', 'dense_7/bias:0'].

Solution - Pass the training labels in model.fit() and your error will be fixed.

Modified,

model.fit(X , epochs=150, batch_size=10, verbose=0)

to

model.fit(X , Y, epochs=150, batch_size=10, verbose=0)

Code -

%tensorflow_version 2.x
# MLP for Pima Indians Dataset saved to single file
import numpy as np
from numpy import loadtxt
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# load pima indians dataset
dataset = np.loadtxt("/content/pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# define model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Model Summary
#model.summary()

# Fit the model
model.fit(X , Y, epochs=150, batch_size=10, verbose=0)

Output -

2.2.0
<tensorflow.python.keras.callbacks.History at 0x7f9208433eb8>

Hope this answers your question. Happy Learning.