sklearn classification_report ValueError: Found input variables with inconsistent numbers of samples: [18, 576] - tensorflow

Question

I'm working on a CNN classification problem. I used keras and a pre-trained model. Now I want to evaluate my model and need the precision, recall and f1-Score. When I use sklearn.metrics classification_report I get above error. I know where the numbers are coming from, first is the length of my test dataset in batches and second are the number of actual sampels (predictions) in there. However I don't know how to "convert" them.
See my code down below:
# load train_ds
train_ds = tf.keras.utils.image_dataset_from_directory(
directory ='/gdrive/My Drive/Flies_dt/224x224',
image_size = (224, 224),
validation_split = 0.40,
subset = "training",
seed = 123,
shuffle = True)
# load val_ds
val_ds = tf.keras.utils.image_dataset_from_directory(
directory ='/gdrive/My Drive/Flies_dt/224x224',
image_size = (224, 224),
validation_split = 0.40,
subset = "validation",
seed = 123,
shuffle = True)
# move some batches of val_ds to test_ds
test_ds = val_ds.take((1*len(val_ds)) // 2)
print('test_ds =', len(test_ds))
val_ds = val_ds.skip((1*len(val_ds)) // 2)
print('val_ds =', len(val_ds)) #test_ds = 18 val_ds = 18
# Load Model
base_model = keras.applications.vgg19.VGG19(
include_top=False,
weights='imagenet',
input_shape=(224,224,3)
)
# Freeze base_model
base_model.trainable = False
#
inputs = keras.Input(shape=(224,224,3))
x = data_augmentation(inputs) #apply data augmentation
# Preprocessing
x = tf.keras.applications.vgg19.preprocess_input(x)
# The base model contains batchnorm layers. We want to keep them in inference mode
# when we unfreeze the base model for fine-tuning, so we make sure that the
# base_model is running in inference mode here.
x = base_model(x, training=False)
x = keras.layers.GlobalAveragePooling2D()(x)
x = keras.layers.Dropout(0.2)(x) # Regularize with dropout
outputs = keras.layers.Dense(5, activation="softmax")(x)
model = keras.Model(inputs, outputs)
model.compile(
loss="sparse_categorical_crossentropy",
optimizer="Adam",
metrics=['acc']
)
model.fit(train_ds, epochs=8, validation_data=val_ds, callbacks=[tensorboard_callback])
# Unfreeze the base_model. Note that it keeps running in inference mode
# since we passed `training=False` when calling it. This means that
# the batchnorm layers will not update their batch statistics.
# This prevents the batchnorm layers from undoing all the training
# we've done so far.
base_model.trainable = True
model.summary()
model.compile(
optimizer=keras.optimizers.Adam(learning_rate=0.000001), # Low learning rate
loss="sparse_categorical_crossentropy",
metrics=['acc']
)
model.fit(train_ds, epochs=5, validation_data=val_ds)
#Evaluate
from sklearn.metrics import classification_report
y_pred = model.predict(test_ds, batch_size=64, verbose=1)
y_pred_bool = np.argmax(y_pred, axis=1)
print(classification_report(test_ds, y_pred_bool))
I also tried something like this, but I'm not sure if this gives me the correct values for multiclass classification.
from keras import backend as K
def recall_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
recall = true_positives / (possible_positives + K.epsilon())
return recall
def precision_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def f1_m(y_true, y_pred):
precision = precision_m(y_true, y_pred)
recall = recall_m(y_true, y_pred)
return 2*((precision*recall)/(precision+recall+K.epsilon()))
# compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc',f1_m,precision_m, recall_m])
# fit the model
history = model.fit(Xtrain, ytrain, validation_split=0.3, epochs=10, verbose=0)
# evaluate the model
loss, accuracy, f1_score, precision, recall = model.evaluate(Xtest, ytest, verbose=0)
This is a lot, Sorry. Hope somebody can help.