Note
Go to the end to download the full example code
Tensorflow/Keras#
Note
This example requires the tensorflow package to be installed.
Theoretically, tpcp is framework agnostic and can be used with any framework. However, due to the way some frameworks handle their objects, some special handling internally is required. Hence, this example does not only serve as example on how to use tensorflow with tpcp, but also as a test case for these special cases.
When using tpcp with any machine learning framework, you either want to use a pretrained model with a normal pipeline or a train your own model as part of an Optimizable Pipeline. Here we show the second case, as it is more complex, and you are likely able to figure out the first case yourself.
This means, we are planning to perform the following steps:
Create a pipeline that creates and trains a model.
Allow the modification of model hyperparameters.
Run a simple cross-validation to demonstrate the functionality.
This example reimplements the basic MNIST example from the [tensorflow documentation](https://www.tensorflow.org/tutorials/keras/classification).
Some Notes#
In this example we show how to implement a Pipeline that uses tensorflow. You could implement an Algorithm in a similar way. This would actually be easier, as no specific handling of the input data would be required. For a pipeline, we need to create a custom Dataset class, as this is the expected input for a pipeline.
The Dataset#
We are using the normal fashion MNIST dataset for this example It consists of 60.000 images of 28x28 pixels, each with a label. We will ignore the typical train-test split, as we want to do our own cross-validation.
In addition, we will simulate an additional “index level”. In this (and most typical deep learning datasets), each datapoint is one vector for which we can make one prediction. In tpcp, we usually deal with datasets, where you might have multiple pieces of information for each datapoint. For example, one datapoint could be a patient, for which we have an entire time series of measurements. We will simulate this here, by creating the index of our dataset as 1000 groups each containing 60 images.
Other than that, the dataset is pretty standard.
Besides the create_index method, we only need to implement the input_as_array and labels_as_array methods that
allow us to easily access the data once we selected a single group.
from functools import lru_cache
import numpy as np
import pandas as pd
import tensorflow as tf
from tpcp import Dataset
tf.keras.utils.set_random_seed(812)
tf.config.experimental.enable_op_determinism()
@lru_cache(maxsize=1)
def get_fashion_mnist_data():
# Note: We throw train and test sets together, as we don't care about the official split here.
# We will create our own split later.
(train_images, train_labels), (test_images, test_labels) = (
tf.keras.datasets.fashion_mnist.load_data()
)
return np.array(list(train_images) + list(test_images)), list(
train_labels
) + list(test_labels)
class FashionMNIST(Dataset):
def input_as_array(self) -> np.ndarray:
self.assert_is_single(None, "input_as_array")
group_id = int(self.group_label.group_id)
images, _ = get_fashion_mnist_data()
return (
images[group_id * 60 : (group_id + 1) * 60].reshape((60, 28, 28))
/ 255
)
def labels_as_array(self) -> np.ndarray:
self.assert_is_single(None, "labels_as_array")
group_id = int(self.group_label.group_id)
_, labels = get_fashion_mnist_data()
return np.array(labels[group_id * 60 : (group_id + 1) * 60])
def create_index(self) -> pd.DataFrame:
# There are 60.000 images in total.
# We simulate 1000 groups of 60 images each.
return pd.DataFrame({"group_id": list(range(1000))})
We can see our Dataset works as expected:
dataset = FashionMNIST()
dataset[0].input_as_array().shape
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz
0/29515 ━━━━━━━━━━━━━━━━━━━━ 0s 0s/step
29515/29515 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz
0/26421880 ━━━━━━━━━━━━━━━━━━━━ 0s 0s/step
147456/26421880 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step
1056768/26421880 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step
5668864/26421880 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
13606912/26421880 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
23175168/26421880 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
26421880/26421880 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz
0/5148 ━━━━━━━━━━━━━━━━━━━━ 0s 0s/step
5148/5148 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz
0/4422102 ━━━━━━━━━━━━━━━━━━━━ 0s 0s/step
303104/4422102 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
1515520/4422102 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
4422102/4422102 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
(60, 28, 28)
dataset[0].labels_as_array().shape
(60,)
The Pipeline#
We will create a pipeline that uses a simple neural network to classify the images.
In tpcp, all “things” that should be optimized need to be parameters.
This means our model itself needs to be a parameter of the pipeline.
However, as we don’t have the model yet, as its creation depends on other hyperparameters, we add it as an optional
parameter initialized with None.
Further, we prefix the parameter name with an underscore, to signify, that this is not a parameter that should be
modified manually by the user.
This is just convention, and it is up to you to decide how you want to name your parameters.
We further introduce a hyperparameter n_dense_layer_nodes to show how we can influence the model creation.
The optimize method#
To make our pipeline optimizable, it needs to inherit from OptimizablePipeline.
Further we need to mark at least one of the parameters as OptiPara using the type annotation.
We do this for our _model parameter.
Finally, we need to implement the self_optimize method.
This method will get the entire training dataset as input and should update the _model parameter with the trained
model.
Hence, we first extract the relevant data (remember, each datapoint is 60 images), by concatinating all images over
all groups in the dataset.
Then we create the Keras model based on the hyperparameters.
Finally, we train the model and update the _model parameter.
Here we chose to wrap the method with make_optimize_safe.
This decorator will perform some runtime checks to ensure that the method is implemented correctly.
The run method#
The run method expects that the _model parameter is already set (i.e. the pipeline was already optimized).
It gets a single datapoint as input (remember, a datapoint is a single group of 60 images).
We then extract the data from the datapoint and let the model make a prediction.
We store the prediction on our output attribute predictions_.
The trailing underscore is a convention to signify, that this is an “result” attribute.
import warnings
from typing import Optional
from tpcp import (
OptimizablePipeline,
OptiPara,
make_action_safe,
make_optimize_safe,
)
from typing_extensions import Self
class KerasPipeline(OptimizablePipeline):
n_dense_layer_nodes: int
n_train_epochs: int
_model: OptiPara[Optional[tf.keras.Sequential]]
predictions_: np.ndarray
def __init__(
self,
n_dense_layer_nodes=128,
n_train_epochs=5,
_model: Optional[tf.keras.Sequential] = None,
):
self.n_dense_layer_nodes = n_dense_layer_nodes
self.n_train_epochs = n_train_epochs
self._model = _model
@property
def predicted_labels_(self):
return np.argmax(self.predictions_, axis=1)
@make_optimize_safe
def self_optimize(self, dataset, **_) -> Self:
data = tf.convert_to_tensor(
np.vstack([d.input_as_array() for d in dataset])
)
labels = tf.convert_to_tensor(
np.hstack([d.labels_as_array() for d in dataset])
)
print(data.shape)
if self._model is not None:
warnings.warn("Overwriting existing model!")
self._model = tf.keras.Sequential(
[
tf.keras.layers.Input((28, 28)),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(
self.n_dense_layer_nodes, activation="relu"
),
tf.keras.layers.Dense(10),
]
)
self._model.compile(
optimizer="adam",
loss=tf.keras.losses.SparseCategoricalCrossentropy(
from_logits=True
),
metrics=["accuracy"],
)
self._model.fit(data, labels, epochs=self.n_train_epochs)
return self
@make_action_safe
def run(self, datapoint) -> Self:
if self._model is None:
raise RuntimeError("Model not trained yet!")
data = tf.convert_to_tensor(datapoint.input_as_array())
self.predictions_ = self._model.predict(data)
return self
Testing the pipeline#
We can now test our pipeline.
We will run the optimization using a couple of datapoints (to keep everything fast) and then use run to get the
predictions for a single unseen datapoint.
pipeline = KerasPipeline().self_optimize(FashionMNIST()[:10])
p1 = pipeline.run(FashionMNIST()[11])
print(p1.predicted_labels_)
print(FashionMNIST()[11].labels_as_array())
(600, 28, 28)
Epoch 1/5
1/19 ━━━━━━━━━━━━━━━━━━━━ 12s 697ms/step - accuracy: 0.1250 - loss: 2.3593
19/19 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.4933 - loss: 1.5112
Epoch 2/5
1/19 ━━━━━━━━━━━━━━━━━━━━ 0s 15ms/step - accuracy: 0.7188 - loss: 1.0003
19/19 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7167 - loss: 0.8663
Epoch 3/5
1/19 ━━━━━━━━━━━━━━━━━━━━ 0s 16ms/step - accuracy: 0.7812 - loss: 0.7427
19/19 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7800 - loss: 0.6830
Epoch 4/5
1/19 ━━━━━━━━━━━━━━━━━━━━ 0s 16ms/step - accuracy: 0.7812 - loss: 0.6089
19/19 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8133 - loss: 0.5658
Epoch 5/5
1/19 ━━━━━━━━━━━━━━━━━━━━ 0s 15ms/step - accuracy: 0.7812 - loss: 0.5329
19/19 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8433 - loss: 0.4940
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
[8 8 6 9 4 0 7 3 7 9 4 8 4 3 7 8 1 4 0 7 9 8 5 5 2 1 3 4 1 9 7 5 9 9 7 8 2
7 4 7 2 4 7 1 1 7 5 4 8 3 5 9 0 7 4 0 0 9 1 9]
[8 8 0 9 2 0 7 3 7 9 3 8 4 3 7 8 1 4 0 7 9 8 5 5 2 1 3 4 6 7 7 5 9 9 7 8 2
7 4 7 0 3 5 1 1 5 5 2 8 3 5 9 0 7 3 0 0 7 1 9]
We can see that even with just 5 epochs, the model already performs quite well. To quantify we can calculate the accuracy for this datapoint:
from sklearn.metrics import accuracy_score
accuracy_score(p1.predicted_labels_, FashionMNIST()[11].labels_as_array())
0.8
Cross Validation#
If we want to run a cross validation, we need to formalize the scoring into a function. We will calculate two types of accuracy: First, the accuracy per group and second, the accuracy over all images across all groups. For more information about how this works, check the Custom Scorer example.
from collections.abc import Sequence
from tpcp.validate import Aggregator
class SingleValueAccuracy(Aggregator[tuple[np.ndarray, np.ndarray]]):
def aggregate(
self, /, values: Sequence[tuple[np.ndarray, np.ndarray]], **_
) -> dict[str, float]:
return {
"accuracy": accuracy_score(
np.hstack([v[0] for v in values]),
np.hstack([v[1] for v in values]),
)
}
single_value_accuracy = SingleValueAccuracy()
def scoring(pipeline, datapoint):
result: np.ndarray = pipeline.safe_run(datapoint).predicted_labels_
reference = datapoint.labels_as_array()
return {
"accuracy": accuracy_score(result, reference),
"per_sample": single_value_accuracy((result, reference)),
}
Now we can run a cross validation. We will only run it on a subset of the data, to keep the runtime manageable.
Note
You might see warnings about retracing of the model. This is because we clone the pipeline before each call to the run method. This is a good idea to ensure that all pipelines are independent of each other, however, might result in some performance overhead.
from tpcp.optimize import Optimize
from tpcp.validate import cross_validate
pipeline = KerasPipeline(n_train_epochs=10)
cv_results = cross_validate(
Optimize(pipeline), FashionMNIST()[:100], scoring=scoring, cv=3
)
CV Folds: 0%| | 0/3 [00:00<?, ?it/s](3960, 28, 28)
Epoch 1/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1:02 506ms/step - accuracy: 0.0938 - loss: 2.5074
28/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.3385 - loss: 1.7902
57/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.4489 - loss: 1.5066
86/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5104 - loss: 1.3483
115/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5500 - loss: 1.2482
124/124 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.6919 - loss: 0.8968
Epoch 2/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.4848
30/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7859 - loss: 0.6226
60/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7918 - loss: 0.6031
90/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7956 - loss: 0.5919
120/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7985 - loss: 0.5869
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8111 - loss: 0.5677
Epoch 3/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 9s 78ms/step - accuracy: 0.8438 - loss: 0.4153
29/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8142 - loss: 0.5231
58/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8235 - loss: 0.5092
88/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8274 - loss: 0.5019
118/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8290 - loss: 0.5004
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8351 - loss: 0.4936
Epoch 4/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.3588
29/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8314 - loss: 0.4573
59/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8386 - loss: 0.4506
88/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8402 - loss: 0.4481
117/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8417 - loss: 0.4488
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8482 - loss: 0.4475
Epoch 5/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.3387
29/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8470 - loss: 0.4151
59/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8519 - loss: 0.4119
88/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8537 - loss: 0.4107
118/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8554 - loss: 0.4118
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8614 - loss: 0.4122
Epoch 6/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.8750 - loss: 0.3044
29/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8600 - loss: 0.3743
59/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8629 - loss: 0.3765
89/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8629 - loss: 0.3784
119/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8636 - loss: 0.3806
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8674 - loss: 0.3840
Epoch 7/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.9062 - loss: 0.2879
30/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8622 - loss: 0.3450
59/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8661 - loss: 0.3492
89/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8675 - loss: 0.3519
119/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8690 - loss: 0.3541
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8742 - loss: 0.3577
Epoch 8/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.8750 - loss: 0.2663
29/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8691 - loss: 0.3194
59/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8741 - loss: 0.3255
88/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8763 - loss: 0.3289
117/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8777 - loss: 0.3314
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8828 - loss: 0.3357
Epoch 9/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.9375 - loss: 0.2468
30/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8889 - loss: 0.2967
58/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8882 - loss: 0.3027
87/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8880 - loss: 0.3061
117/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8880 - loss: 0.3091
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8902 - loss: 0.3147
Epoch 10/10
1/124 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.9375 - loss: 0.2620
30/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8989 - loss: 0.2791
60/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8965 - loss: 0.2855
90/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2889
121/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2915
124/124 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8955 - loss: 0.2970
Datapoints: 0%| | 0/34 [00:00<?, ?it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 3%|▎ | 1/34 [00:00<00:04, 7.73it/s]WARNING:tensorflow:5 out of the last 5 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x7cb9f20bd630> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/stepWARNING:tensorflow:6 out of the last 6 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x7cb9f20bd630> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
Datapoints: 6%|▌ | 2/34 [00:00<00:04, 7.22it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 9%|▉ | 3/34 [00:00<00:04, 7.47it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 12%|█▏ | 4/34 [00:00<00:03, 7.69it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 15%|█▍ | 5/34 [00:00<00:03, 7.73it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 18%|█▊ | 6/34 [00:00<00:03, 7.83it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 21%|██ | 7/34 [00:00<00:03, 7.92it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 24%|██▎ | 8/34 [00:01<00:03, 7.89it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 26%|██▋ | 9/34 [00:01<00:03, 7.95it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 40ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
Datapoints: 29%|██▉ | 10/34 [00:01<00:03, 7.83it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 32%|███▏ | 11/34 [00:01<00:02, 7.81it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 35%|███▌ | 12/34 [00:01<00:02, 7.91it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 38%|███▊ | 13/34 [00:01<00:02, 7.99it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 41%|████ | 14/34 [00:01<00:02, 7.95it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 44%|████▍ | 15/34 [00:01<00:02, 8.03it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 47%|████▋ | 16/34 [00:02<00:02, 8.09it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 50%|█████ | 17/34 [00:02<00:02, 8.02it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 53%|█████▎ | 18/34 [00:02<00:01, 8.05it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 56%|█████▌ | 19/34 [00:02<00:01, 8.04it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 59%|█████▉ | 20/34 [00:02<00:01, 7.98it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 62%|██████▏ | 21/34 [00:02<00:01, 8.04it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 65%|██████▍ | 22/34 [00:02<00:01, 8.05it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 68%|██████▊ | 23/34 [00:02<00:01, 7.98it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 71%|███████ | 24/34 [00:03<00:01, 8.04it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 74%|███████▎ | 25/34 [00:03<00:01, 8.02it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 76%|███████▋ | 26/34 [00:03<00:01, 7.90it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
Datapoints: 79%|███████▉ | 27/34 [00:03<00:00, 7.86it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 82%|████████▏ | 28/34 [00:03<00:00, 7.90it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 85%|████████▌ | 29/34 [00:03<00:00, 7.84it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 88%|████████▊ | 30/34 [00:03<00:00, 7.89it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 91%|█████████ | 31/34 [00:03<00:00, 7.98it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 94%|█████████▍| 32/34 [00:04<00:00, 7.90it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 97%|█████████▋| 33/34 [00:04<00:00, 7.93it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 100%|██████████| 34/34 [00:04<00:00, 7.98it/s]
Datapoints: 100%|██████████| 34/34 [00:04<00:00, 7.92it/s]
CV Folds: 33%|███▎ | 1/3 [00:07<00:15, 7.80s/it](4020, 28, 28)
Epoch 1/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1:46 854ms/step - accuracy: 0.1250 - loss: 2.3656
29/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.3836 - loss: 1.7793
60/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.4882 - loss: 1.5002
89/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5386 - loss: 1.3562
118/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5732 - loss: 1.2562
126/126 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.7000 - loss: 0.8913
Epoch 2/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 2s 16ms/step - accuracy: 0.8438 - loss: 0.4830
30/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7651 - loss: 0.6239
59/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7679 - loss: 0.6215
89/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7733 - loss: 0.6147
118/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7776 - loss: 0.6073
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7968 - loss: 0.5690
Epoch 3/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.8750 - loss: 0.3561
30/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8123 - loss: 0.5195
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8127 - loss: 0.5228
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8151 - loss: 0.5196
121/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8172 - loss: 0.5157
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8284 - loss: 0.4927
Epoch 4/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.9375 - loss: 0.3082
30/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8371 - loss: 0.4758
59/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8335 - loss: 0.4832
88/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8346 - loss: 0.4805
118/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8360 - loss: 0.4768
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8453 - loss: 0.4533
Epoch 5/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.3008
31/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8347 - loss: 0.4364
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8379 - loss: 0.4387
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8412 - loss: 0.4354
121/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8440 - loss: 0.4323
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8570 - loss: 0.4134
Epoch 6/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.2896
29/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8404 - loss: 0.4047
60/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8461 - loss: 0.4068
90/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8509 - loss: 0.4037
120/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8540 - loss: 0.4010
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8674 - loss: 0.3836
Epoch 7/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.2921
30/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8363 - loss: 0.3789
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8447 - loss: 0.3802
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8512 - loss: 0.3768
120/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8552 - loss: 0.3743
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8724 - loss: 0.3583
Epoch 8/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.2784
29/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8487 - loss: 0.3543
57/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8546 - loss: 0.3569
87/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8606 - loss: 0.3540
117/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8643 - loss: 0.3519
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8801 - loss: 0.3375
Epoch 9/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.2839
29/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8580 - loss: 0.3369
59/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8634 - loss: 0.3369
89/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8688 - loss: 0.3333
119/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8725 - loss: 0.3312
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8873 - loss: 0.3178
Epoch 10/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.2753
32/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8639 - loss: 0.3167
59/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8703 - loss: 0.3170
89/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8763 - loss: 0.3138
120/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8800 - loss: 0.3118
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8940 - loss: 0.3003
Datapoints: 0%| | 0/33 [00:00<?, ?it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 3%|▎ | 1/33 [00:00<00:04, 8.00it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 6%|▌ | 2/33 [00:00<00:03, 7.92it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 9%|▉ | 3/33 [00:00<00:03, 8.00it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 12%|█▏ | 4/33 [00:00<00:03, 8.08it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
Datapoints: 15%|█▌ | 5/33 [00:00<00:03, 8.01it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 18%|█▊ | 6/33 [00:00<00:03, 8.06it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 21%|██ | 7/33 [00:00<00:03, 8.07it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 24%|██▍ | 8/33 [00:01<00:03, 7.94it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 27%|██▋ | 9/33 [00:01<00:03, 7.98it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
Datapoints: 30%|███ | 10/33 [00:01<00:02, 7.94it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 46ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 33%|███▎ | 11/33 [00:01<00:02, 7.70it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 36%|███▋ | 12/33 [00:01<00:02, 7.80it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 39%|███▉ | 13/33 [00:01<00:02, 7.76it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 42%|████▏ | 14/33 [00:01<00:02, 7.77it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 45%|████▌ | 15/33 [00:01<00:02, 7.90it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 48%|████▊ | 16/33 [00:02<00:02, 7.97it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 52%|█████▏ | 17/33 [00:02<00:02, 7.96it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 55%|█████▍ | 18/33 [00:02<00:01, 8.03it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
Datapoints: 58%|█████▊ | 19/33 [00:02<00:01, 7.99it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 61%|██████ | 20/33 [00:02<00:01, 7.94it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 64%|██████▎ | 21/33 [00:02<00:01, 8.03it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 67%|██████▋ | 22/33 [00:02<00:01, 8.09it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 38ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
Datapoints: 70%|██████▉ | 23/33 [00:02<00:01, 7.98it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 73%|███████▎ | 24/33 [00:03<00:01, 8.02it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 76%|███████▌ | 25/33 [00:03<00:00, 8.05it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 79%|███████▉ | 26/33 [00:03<00:00, 7.93it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 82%|████████▏ | 27/33 [00:03<00:00, 7.86it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 85%|████████▍ | 28/33 [00:03<00:00, 7.89it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
Datapoints: 88%|████████▊ | 29/33 [00:03<00:00, 7.92it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 91%|█████████ | 30/33 [00:03<00:00, 8.03it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 94%|█████████▍| 31/33 [00:03<00:00, 8.08it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 37ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 97%|█████████▋| 32/33 [00:04<00:00, 7.99it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 100%|██████████| 33/33 [00:04<00:00, 8.09it/s]
Datapoints: 100%|██████████| 33/33 [00:04<00:00, 7.97it/s]
CV Folds: 67%|██████▋ | 2/3 [00:15<00:07, 7.86s/it](4020, 28, 28)
Epoch 1/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1:01 491ms/step - accuracy: 0.0938 - loss: 2.3129
31/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.4081 - loss: 1.7067
60/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.4927 - loss: 1.4764
90/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5423 - loss: 1.3375
120/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5767 - loss: 1.2404
126/126 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.6983 - loss: 0.8965
Epoch 2/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 2s 16ms/step - accuracy: 0.8125 - loss: 0.4789
28/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7854 - loss: 0.6090
57/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7841 - loss: 0.6126
86/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7865 - loss: 0.6102
114/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7886 - loss: 0.6056
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8005 - loss: 0.5778
Epoch 3/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.8750 - loss: 0.3564
28/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8293 - loss: 0.5023
57/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8226 - loss: 0.5134
87/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8222 - loss: 0.5153
117/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8224 - loss: 0.5142
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8269 - loss: 0.5017
Epoch 4/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.9062 - loss: 0.3024
31/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8519 - loss: 0.4437
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8461 - loss: 0.4542
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8446 - loss: 0.4578
121/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8440 - loss: 0.4582
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8458 - loss: 0.4515
Epoch 5/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 16ms/step - accuracy: 0.9062 - loss: 0.2785
30/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8667 - loss: 0.4055
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8611 - loss: 0.4168
90/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8591 - loss: 0.4206
120/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8582 - loss: 0.4211
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8585 - loss: 0.4165
Epoch 6/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 9s 75ms/step - accuracy: 0.9062 - loss: 0.2679
30/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8788 - loss: 0.3689
60/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8742 - loss: 0.3803
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8724 - loss: 0.3852
123/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8713 - loss: 0.3866
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8719 - loss: 0.3833
Epoch 7/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.9375 - loss: 0.2306
31/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8873 - loss: 0.3419
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8835 - loss: 0.3515
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8821 - loss: 0.3569
122/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8813 - loss: 0.3592
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8823 - loss: 0.3594
Epoch 8/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.9375 - loss: 0.2117
29/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.3182
59/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8897 - loss: 0.3293
89/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8883 - loss: 0.3347
119/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8875 - loss: 0.3367
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8886 - loss: 0.3366
Epoch 9/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 1s 15ms/step - accuracy: 0.9375 - loss: 0.2051
31/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.3004
62/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.3094
91/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.3139
120/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.3156
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8973 - loss: 0.3152
Epoch 10/10
1/126 ━━━━━━━━━━━━━━━━━━━━ 2s 16ms/step - accuracy: 0.9375 - loss: 0.1920
31/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8986 - loss: 0.2829
61/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8981 - loss: 0.2920
90/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8981 - loss: 0.2970
118/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8985 - loss: 0.2991
126/126 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.3000
Datapoints: 0%| | 0/33 [00:00<?, ?it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 3%|▎ | 1/33 [00:00<00:03, 8.29it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 6%|▌ | 2/33 [00:00<00:03, 8.09it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 9%|▉ | 3/33 [00:00<00:03, 8.04it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 12%|█▏ | 4/33 [00:00<00:03, 8.12it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 39ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 15%|█▌ | 5/33 [00:00<00:03, 7.90it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 18%|█▊ | 6/33 [00:00<00:03, 8.03it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 21%|██ | 7/33 [00:00<00:03, 8.11it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 24%|██▍ | 8/33 [00:00<00:03, 8.04it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 27%|██▋ | 9/33 [00:01<00:02, 8.05it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 30%|███ | 10/33 [00:01<00:02, 8.06it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 33%|███▎ | 11/33 [00:01<00:02, 7.99it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 36%|███▋ | 12/33 [00:01<00:02, 8.00it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 39%|███▉ | 13/33 [00:01<00:02, 8.01it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 35ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 42%|████▏ | 14/33 [00:01<00:02, 7.92it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 45%|████▌ | 15/33 [00:01<00:02, 7.97it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 48%|████▊ | 16/33 [00:01<00:02, 8.00it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 52%|█████▏ | 17/33 [00:02<00:02, 7.94it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 55%|█████▍ | 18/33 [00:02<00:01, 8.03it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 58%|█████▊ | 19/33 [00:02<00:01, 8.11it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 61%|██████ | 20/33 [00:02<00:01, 8.06it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 64%|██████▎ | 21/33 [00:02<00:01, 8.15it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 67%|██████▋ | 22/33 [00:02<00:01, 8.15it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 36ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 70%|██████▉ | 23/33 [00:02<00:01, 8.04it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 73%|███████▎ | 24/33 [00:02<00:01, 8.05it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 76%|███████▌ | 25/33 [00:03<00:00, 8.07it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 79%|███████▉ | 26/33 [00:03<00:00, 7.97it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 82%|████████▏ | 27/33 [00:03<00:00, 8.06it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 85%|████████▍ | 28/33 [00:03<00:00, 8.11it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 32ms/step
Datapoints: 88%|████████▊ | 29/33 [00:03<00:00, 8.02it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 91%|█████████ | 30/33 [00:03<00:00, 8.02it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 94%|█████████▍| 31/33 [00:03<00:00, 8.07it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 34ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 31ms/step
Datapoints: 97%|█████████▋| 32/33 [00:03<00:00, 7.98it/s]
1/2 ━━━━━━━━━━━━━━━━━━━━ 0s 33ms/step
2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 30ms/step
Datapoints: 100%|██████████| 33/33 [00:04<00:00, 8.03it/s]
Datapoints: 100%|██████████| 33/33 [00:04<00:00, 8.04it/s]
CV Folds: 100%|██████████| 3/3 [00:23<00:00, 7.75s/it]
CV Folds: 100%|██████████| 3/3 [00:23<00:00, 7.77s/it]
We can now look at the results per group:
cv_results["test__single__accuracy"]
[[0.8333333333333334, 0.8333333333333334, 0.9166666666666666, 0.7666666666666667, 0.8166666666666667, 0.8166666666666667, 0.8, 0.8333333333333334, 0.8333333333333334, 0.85, 0.7666666666666667, 0.8333333333333334, 0.8666666666666667, 0.85, 0.8833333333333333, 0.8666666666666667, 0.8333333333333334, 0.8333333333333334, 0.8, 0.8333333333333334, 0.7833333333333333, 0.7166666666666667, 0.8166666666666667, 0.8333333333333334, 0.8333333333333334, 0.8833333333333333, 0.8833333333333333, 0.85, 0.85, 0.75, 0.75, 0.85, 0.8166666666666667, 0.8833333333333333], [0.8, 0.9, 0.75, 0.8666666666666667, 0.8833333333333333, 0.8166666666666667, 0.8833333333333333, 0.8833333333333333, 0.8333333333333334, 0.8, 0.85, 0.8, 0.8166666666666667, 0.8, 0.7833333333333333, 0.8, 0.8166666666666667, 0.7666666666666667, 0.85, 0.75, 0.8, 0.8333333333333334, 0.7666666666666667, 0.9, 0.8, 0.7833333333333333, 0.8166666666666667, 0.8666666666666667, 0.8833333333333333, 0.9166666666666666, 0.7333333333333333, 0.7833333333333333, 0.9], [0.7833333333333333, 0.9333333333333333, 0.75, 0.8333333333333334, 0.8833333333333333, 0.8666666666666667, 0.8833333333333333, 0.9, 0.9, 0.9, 0.9166666666666666, 0.85, 0.8666666666666667, 0.8833333333333333, 0.85, 0.8, 0.9166666666666666, 0.75, 0.7166666666666667, 0.8666666666666667, 0.8166666666666667, 0.75, 0.7833333333333333, 0.7333333333333333, 0.8666666666666667, 0.8833333333333333, 0.9166666666666666, 0.8, 0.8666666666666667, 0.9, 0.85, 0.85, 0.9]]
Average first per group and then over all groups:
cv_results["test__agg__accuracy"]
array([0.82843137, 0.82525253, 0.84747475])
And the overall accuracy as the average over all samples of all groups within a fold:
cv_results["test__agg__per_sample__accuracy"]
array([0.82843137, 0.82525253, 0.84747475])
Total running time of the script: (0 minutes 37.559 seconds)
Estimated memory usage: 852 MB