# Model.predict() output **URL:** \ **Category:** Curriculum Help\ **Tags:** python\ **Created:** [July 22, 2021, 1:55am UTC](https://forum.freecodecamp.org/t/model-predict-output/470349 "2021-07-22T01:55:53Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![solgeller3](https://sea3.discourse-cdn.com/freecodecamp/user_avatar/forum.freecodecamp.org/solgeller3/32/183391_2.png) [@solgeller3](https://forum.freecodecamp.org/u/solgeller3)\ **Post date:** [July 22, 2021, 1:55am UTC](https://forum.freecodecamp.org/t/model-predict-output/470349/1 "2021-07-22T01:55:53Z")
Hey, So I have this model which is pretrained by Google and also trained on a tfds dataset: ```auto import matplotlib.pyplot as plt import tensorflow as tf import tensorflow_datasets as tfds keras = tf.keras # split the data manually into 80% training, 10% testing, 10% validation (raw_train, raw_validation, raw_test), metadata = tfds.load( 'cats_vs_dogs', split=['train[:80%]', 'train[80%:90%]', 'train[90%:]'], with_info=True, as_supervised=True, ) """"" Since the sizes of our images are all different, we need to convert them all to the same size. We can create a function that will do that for us below. """"" IMG_SIZE = 160 # All images will be resized to 160x160 def format_example(img, lab): """ returns an image that is reshaped to IMG_SIZE """ img = tf.cast(img, tf.float32) img = (img / 127.5) - 1 img = tf.image.resize(img, (IMG_SIZE, IMG_SIZE)) img = tf.expand_dims(img, axis=0) return img, lab # Now we can apply this function to all our images using .map(). # .map() takes every single example in raw_train, raw_validation, etc and applies the function to it train = raw_train.map(format_example) validation = raw_validation.map(format_example) test = raw_test.map(format_example) BATCH_SIZE = 32 SHUFFLE_BUFFER_SIZE = 1000 # Finally we will shuffle and batch the images train_batches = train.shuffle(SHUFFLE_BUFFER_SIZE).batch(BATCH_SIZE) validation_batches = validation.batch(BATCH_SIZE) test_batches = test.batch(BATCH_SIZE) IMG_SHAPE = (IMG_SIZE, IMG_SIZE, 3) # Create the base model from the pre-trained model MobileNet V2 base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE, include_top=False, # we don't want to load the top layer weights='imagenet') base_model.trainable = False """"" Adding OUR Classifier """"" global_average_layer = tf.keras.layers.GlobalAveragePooling2D() # Finally, we will add the prediction layer that will be a single dense neuron. We can do this because we # only have two classes to predict for. prediction_layer = keras.layers.Dense(1, activation='sigmoid') # Now we will combine these layers together in a model. model = tf.keras.Sequential([ base_model, global_average_layer, prediction_layer ]) # TRAINING THE MODEL """"" Now we will train and compile the model. We will use a very small learning rate to ensure that the model does not have any major changes made to it. """"" base_learning_rate = 0.0001 model.compile(optimizer=tf.keras.optimizers.RMSprop(lr=base_learning_rate), loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), metrics=['accuracy']) # Now we can train it on our images initial_epochs = 10 history = model.fit(train_batches, epochs=initial_epochs, validation_data=validation_batches) acc = history.history['accuracy'] print(acc) # you can save a model and load a model with this syntax so you don't have to train it again every time model.save("dogs_vs_cats.h5") # we can save the model and reload it at anytime in the future new_model = tf.keras.models.load_model('dogs_vs_cats.h5') predictions = new_model.predict(test) print(predictions) get_label_name = metadata.features['label'].int2str # creates a function object that we can use to get labels i = 0 for image, label in raw_train.take(6): plt.figure() plt.imshow(image) plt.title(get_label_name(label)) print(get_label_name(label)) print(predictions[i]) i += 1 ``` Anyway, I am getting this output and I don’t know how to use it or understand it: ```auto dog [0.33223754] dog [0.48130825] dog [0.70762724] cat [0.26925486] dog [0.49678028] dog [0.45581067] ``` In the code, I print the label name and the prediction beneath it, but i dont understand what the number inside the array means and how to use it. I would apreciate it if someone could explain. Thamk you! ---
**Author:** ![AndyG](https://sea3.discourse-cdn.com/freecodecamp/user_avatar/forum.freecodecamp.org/andyg/32/232831_2.png) [@AndyG](https://forum.freecodecamp.org/u/AndyG)\ **Post date:** [July 22, 2021, 3:56am UTC](https://forum.freecodecamp.org/t/model-predict-output/470349/2 "2021-07-22T03:56:30Z")
Hello @solgeller3 This is the probability of every single output described in the model. In many classification models you have a threshold. The common threshold is 0.5, if the result is _above_ of this, then is more likely to be “true”. On the contrary if the result is _below_ is more likely to be false. The more easy to understand example of this mechanism is the logistic function. > 1/1+e^-z In the specific context of your model, you are making a classification model with images, and after 10 iterations and at a base learning rate of 0.0001 only the third element, > [@solgeller3](#): > > ```auto > dog > [0.70762724] > > ``` has a strong probability of being classified correctly. To optimize the performance of your model: 1. You can adjust the learning rate. For correctly doing that you must be aware of terms like Gradient descent, Loss Function and Hyper parameter(The learning rate is a Hyperparameter). 2. You can change the number of iterations, since a more number of iterations could make a prediction more accurate. However there is always a risk of over-fitting , this is called bias-variance tradeoff. But…, In simple words, these are the probabilities that your model (at a given learning rate, iterations, and parameters) will classify correctly every one of your images. If you want more information about classification threshold: 1. The basic concept of threshold [طبقه بندی: آستانه  |  Machine Learning  |  Google for Developers](https://developers.google.com/machine-learning/crash-course/classification/thresholding) 2. Additional exercises on keras for having fun [https://keras.io/api/metrics/classification\_metrics/](https://keras.io/api/metrics/classification_metrics/) Hope this helps. ---
**Author:** ![AndyG](https://sea3.discourse-cdn.com/freecodecamp/user_avatar/forum.freecodecamp.org/andyg/32/232831_2.png) [@AndyG](https://forum.freecodecamp.org/u/AndyG)\ **Post date:** [July 22, 2021, 4:03am UTC](https://forum.freecodecamp.org/t/model-predict-output/470349/3 "2021-07-22T04:03:40Z")
> [@solgeller3](#): > > `prediction_layer = keras.layers.Dense(1, activation='sigmoid')` I forgot it, even in this model you are using the sigmoid function to make a prediction. The logistic function is part of the family of sigmoid function. [![](https://upload.wikimedia.org/wikipedia/commons/thumb/5/53/Sigmoid-function-2.svg/1280px-Sigmoid-function-2.svg.png) ](https://upload.wikimedia.org/wikipedia/commons/thumb/5/53/Sigmoid-function-2.svg/1280px-Sigmoid-function-2.svg.png) So a more geometrical explanation would be, the threshold is 0.5 and you can locate every individual output value within the plane: > [@solgeller3](#): > > ```auto > dog > [0.33223754] > dog > [0.48130825] > dog > [0.70762724] > cat > [0.26925486] > dog > [0.49678028] > dog > [0.45581067] > > ``` Hope this helps. ---
**Author:** ![system](https://global.discourse-cdn.com/freecodecamp/original/3X/e/1/e1c433102e34b46dfaa3e15d13ab9a514b127078.svg) [@system](https://forum.freecodecamp.org/u/system)\ **Post date:** [January 20, 2022, 4:04pm UTC](https://forum.freecodecamp.org/t/model-predict-output/470349/4 "2022-01-20T16:04:20Z")
Closed on January 20, 2022, 4:04pm UTC This topic was automatically closed 182 days after the last reply. New replies are no longer allowed.