when feeding a tf.data.Dataset to train EfficientnetB0 model I get the following error:
ValueError: in converted code:
C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py:677 map_fn
batch_size=None)
C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training.py:2410 _standardize_tensors
exception_prefix='input')
C:\Users\fconrad\AppData\Local\Continuum\anaconda3\envs\venv_spielereien\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py:573 standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking input: expected efficientnet-b0_input to have 4 dimensions, but got array with shape (224, 224, 3)
I realy wonder why this happens, since when I create a batch from my Dataset:
train_generator = (tf.data.Dataset
.from_tensor_slices((train_imgs, train_labels))
.map(read_img)
.map(flip_img)
.map(brightness)
.map(blur)
.map(noise)
.map(rotate_90)
.repeat()
.shuffle(512)
.batch(BATCH_SIZE)
.prefetch(True))
validation_generator = (tf.data.Dataset
.from_tensor_slices((validation_imgs, validation_labels))
.map(read_img)
)
print(train_generator.__iter__().__next__()[0].shape)
I get the expected result (64, 224, 224, 3).
But after creating the model the error above raises when I start training:
effn = tfkeras.EfficientNetB0(include_top=False, input_shape=img_shape, classes=4)
effn_model = tf.keras.Sequential()
effn_model.add(effn)
effn_model.add(tf.keras.layers.GlobalAveragePooling2D())
effn_model.add(tf.keras.layers.Dense(4, 'softmax'))
effn_model.compile(optimizer= 'adam', loss='categorical_crossentropy', metrics= ['categorical_accuracy'])
effn_model.fit(train_generator,
epochs=20,
steps_per_epoch=train_imgs.shape[0] // BATCH_SIZE,
validation_data= validation_generator)
Does anyone know why the slices from dataset have shape (64,224,224,3) but the model doesnt recognize the batch dimension? when I try to train a keras.application model, everything works fine.
I use tensorflow 2.1 and the pip install of efficientnet. Thanks
as explained here keras.io/api/applications/efficientnet/
input_shape: Optional shape tuple, only to be specified if include_top is False. It should have exactly 3 inputs channels.
as so try this->
from tensorflow.keras.applications.efficientnet import EfficientNetB0, EfficientNetB5
mm = EfficientNetB0(include_top=True, weights=None, input_tensor=None, input_shape=(128, 128, 3), pooling=None, classes=2, classifier_activation="sigmoid")
mm.summary()
note the input_shape=(128, 128, 3) It has 3 channels.
Related
I am using the keras functional api, but i'm getting an error about the input shape of the model -
ValueError: Input 0 is incompatible with layer financial_model: expected shape=(None, 1, 62), found shape=(1, 62)
samples = np.array(samples, dtype=np.float64)
labels = np.array(labels, dtype=np.uint8)
x_train, x_test, y_train, y_test = train_test_split(samples, labels, test_size=0.33,
random_state=42)
min_max = MinMaxScaler()
x_train = min_max.fit_transform(x_train)
lstm_input = np.expand_dims(x_train, axis=1).shape
inputs = keras.Input(shape=(lstm_input[1],lstm_input[2]))
hidden = keras.layers.LSTM(lstm_input[2], activation='tanh')(inputs)
output = keras.layers.Dense(2)(hidden)
model = keras.Model(inputs=inputs, outputs=output, name="financial_model")
model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=keras.optimizers.Adam(learning_rate=0.001),
metrics=["accuracy"],
)
model.summary()
history = model.fit(x_train, y_train, batch_size=1, epochs=5, validation_split=0.2)
I've learnt from similar questions that the batch size is omitted in the input shape dimensions. How do I feed a 3 dimensional input shape into the lstm layer when the batch size is left out in the input object?
Since I have less than 50 reputation, I cannot comment. I'm not sure of this, but as the error says, your input shape is wrong. You have to add another dimension to it. Try something like this:
inputs = keras.Input(shape=(lstm_input[1],lstm_input[2], 1))
'I want to solve a classification problem by keras.model, but after running model.fit I face to a dimension error. I have run following code:'
print(X_train.shape)
print(y_train.shape)
'output:'
(2588, 39436)
(2588, 6)
model = keras.Sequential(
[
keras.Input(shape=(39436,1)),
layers.Conv1D(32, kernel_size=3, strides=5, activation="relu"),
layers.MaxPooling1D(pool_size=10),
layers.Conv1D(64, kernel_size=3, strides=5, activation="relu"),
layers.MaxPooling1D(pool_size=10),
layers.Flatten(),
layers.Dropout(0.5),
layers.Dense(num_classes, activation="softmax"),
]
)
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
'After running following code, '
model.fit(X_train, y_train, batch_size=128, epochs=15, validation_split=0.3)
'I give this error:'
ValueError: in user code:
ValueError: Input 0 of layer sequential_1 is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: [None, 39436]
'It would be appreciated if you guide me what would be the issue?'
Your input array, as per the error message, has a shape [None, 39436]. However, in your Input layer, you pass in a shape [39436, 1], which matches to [None, 39436, 1] where None represents the samples dimension. This is the error that is being thrown.
You need to match the shapes, either by:
1. Reshaping your input data to have a shape of [samples, 39436, 1], leaving the model architecture unchanged.
This can be done as (suppose train_X are your input features):
train_X = np.expand_dims(train_X, axis=2)
np.expand_dims adds a new dimension to the array at index 2 of the shape of the array. So here it reshapes [samples, 39436] to [samples, 39436, 1].
Refer: NumPy docs for expand_dims
OR
2. Change the input_shape parameter in the Input layer to accept a shape of [39436,], so as to match your data.
When running the model.fit function an error is thrown. The main question is, what does this error mean? The code is run on a TPU V3-8 and uses Google cloud for data retrieval. I did try to look up the error on the web, however I could not find a single case of someone else getting this error.
model.fit(
dataset,
steps_per_epoch = N_IMGS // BATCH_SIZE,
epochs = EPOCHS,
)
Throws the error
InvalidArgumentError: {{function_node __inference_train_function_528542}} Compilation failure: Depth of output must be a multiple of the number of groups: 3 vs 2
[[{{node sequential/conv2d/Conv2D}}]]
TPU compilation failed
[[tpu_compile_succeeded_assert/_15965336225898828069/_5]]
The error message is not clear to me, what exactly is going wrong? The following model is used.
def get_model():
# reset to free memory and training variables
tf.keras.backend.clear_session()
with strategy.scope():
net = efn.EfficientNetB0(include_top=False, weights='noisy-student', input_shape=(HEIGHT, WIDTH, 3))
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(3, (3, 3), padding='same', input_shape=(HEIGHT, WIDTH, 1)),
net,
tf.keras.layers.GlobalAveragePooling2D(),
tf.keras.layers.Dropout(0.25),
tf.keras.layers.Dense(N_LABELS, activation='softmax', dtype='float32'),
])
model.compile(optimizer=tf.keras.optimizers.Adam(), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
return model
model = get_model()
tf.keras.utils.plot_model(model, 'model.png', show_shapes=True)
The dataset gives the following output
for images, labels in dataset.take(1): # only take first element of dataset
print(f'images.shape: {images.shape}, images.dtype: {images.dtype}, labels.shape: {labels.shape}, labels.dtype: {labels.dtype}')
images.shape: (64, 224, 400, 1), images.dtype: <dtype: 'float32'>, labels.shape: (64,), labels.dtype: <dtype: 'int32'>
I am working in keras tensorflow backend on Windows 10.
I am not able to interpret the meaning of the error
Here is a snippet of my code
{
model = Sequential([
#Dense(32, input_shape=(1080,1920,2)),
Dense(32, input_shape=(250,250, 3)),
#Dense(32, input_shape=(3,1080,1920,2)),
Activation('relu'),
Dense(10),
Activation('softmax'),
Dropout(0.02),
])
layer = Dropout(0.02)
#further layers:
model.add(Dense(units=3)) #hidden layer 1
model.add(Dense(units=1)) #output layer
model.add(Conv2D(3, (3, 3)))
model.add(MaxPooling2D(pool_size=(2, 2),strides=None,padding='valid', data_format=None))
model.compile(loss=losses.mean_squared_error, optimizer='sgd')
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
test_generator = ImageDataGenerator()
validation_generator = test_generator.flow_from_directory(
'human_faces/validation',
target_size=(250,250),
batch_size=3,
class_mode=None,classes=0)
model.fit_generator(
train_generator,
steps_per_epoch=1,## batch_size,
#steps_per_epoch=3,
epochs=5,
validation_data=validation_generator,
# validation_steps=61 ) # batch_size)
validation_steps=1)
}
My error:
File "C:/Users/Owner/PycharmProjects/untitled1/work.py", line 89, in
validation_steps=1) ValueError: Error when checking target: expected max_pooling2d_1 to have 4 dimensions, but got array with
shape (61, 1)
There is a mismatch between the shapes of the output of your network (which is the output of the MaxPooling2D layer) and the output you seem to expect (based on the desired "true" output example you feed together with each input to model.fit_generator().
To investigate the mismatch you have to examine your (unshown) code of train_generator to see what output shape you are expecting, and can use model.summary() to see the conflicting output shape generated by the MaxPooling2D layer.
Try adding the following argument to Cov2D:
padding='SAME'
Like:
model.add(Conv2D(3, (3, 3),padding='SAME'))
I'm trying to apply transfer learning to MNIST using MobileNet weights in Keras. Keras documentation to use MobileNet https://keras.io/applications/#mobilenet
Mobilenet accepts 224x224x3 as input but MNIST is 28x28x1. I'm creating a Lambda layer which can convert 28x28x1 image into 224x224x3 and send it as input to MobileNet. The following code causes
TypeError: Input layers to a Model must be InputLayer objects. Received inputs: Tensor("lambda_2/ResizeNearestNeighbor:0", shape=(?, 224, 224, 3), dtype=float32). Input 0 (0-based) originates from layer type Lambda.
height = 28
width = 28
input_image = Input(shape=(height,width,1))
def resize_image_to_inception(x):
x = K.repeat_elements(x, 3, axis=3)
x = K.resize_images(x, 8, 8, data_format="channels_last")
return x
input_image_ = Lambda(resize_image_to_inception, output_shape=(224, 224, 3))(input_image)
print(type(input_image_))
base_model = MobileNet(input_tensor=input_image_, weights='imagenet', include_top=False)