[FIXED] How do i test my CNN model with an image?

Issue

Intro/setup

I am new at programming, and i made my first CNN model from a tutorial. I have set my jupyter/tensorflow/keras up in C:\Users\labadmin

What i have understood is that i just have to put the path from labadmin in order to implement my data for testing and training.

Since i am not sure what is causing the error i have pasted the whole code and error, i think it is about the system not getting the data.

The folder with the Data set-up as following:

labadmin has a folder called data withing that there are two folders training and test

Both cat images and dog images are shuffled in both folders. There are 10000 pictures in each folder, so there should be enough:

The tutorial teaches. 1. How to create a model 2. Define your labels 3. Create your training data 4. Creating and building the layers 5. Create your testing data 6. (from what i understood) the last part of the code i have created is
validating my model.

This is the code

    import cv2
    import numpy as np
    import os
    from random import shuffle
    from tqdm import tqdm

    TRAIN_DIR = "data\\training"
    TEST_DIR = "data\\test"
    IMG_SIZE = 50

    LR = 1e-3

    MODEL_NAME = 'dogvscats-{}-{}.model'.format(LR, '2cov-basic1')

    def label_img(img):
        word_label = img.split('.')[-3]
        if word_label == 'cat': return [1,0]
        elif word_label == 'dog': return [0,1]

    def creat_train_data():
        training_data = []
        for img in tqdm(os.listdir(TRAIN_DIR)):
            label = label_img(img)
            path = os.path.join(TRAIN_DIR,img)
            img = cv2.resize(cv2.imread(path, cv2.IMREAD_GRAYSCALE), (IMG_SIZE,IMG_SIZE))
            training_data.append([np.array(img), np.array(label)])
        shuffle(training_data)
        np.save('training.npy', training_data) #save file
        return training_data

    import tflearn
    from tflearn.layers.conv import conv_2d, max_pool_2d
    from tflearn.layers.core import input_data, dropout, fully_connected
    from tflearn.layers.estimator import regression



    # Building convolutional convnet
    convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
    # http://tflearn.org/layers/conv/
    # http://tflearn.org/activations/
    convnet = conv_2d(convnet, 32, 2, activation='relu')
    convnet = max_pool_2d(convnet, 2)

    convnet = conv_2d(convnet, 64, 2, activation='relu')
    convnet = max_pool_2d(convnet, 2)

    convnet = fully_connected(convnet, 1024, activation='relu')
    convnet = dropout(convnet, 0.8)

    #OUTPUT layer
    convnet = fully_connected(convnet, 2, activation='softmax')
    convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

    model = tflearn.DNN(convnet, tensorboard_dir='log')

    def process_test_data():
        testing_data = []
        for img in tqdm(os.listdir(TEST_DIR)):
            path = os.path.join(TEST_DIR,img)
            img_num = img.split ('.')[0]  #ID of pic=img_num
            img = cv2.resize(cv2-imread(path, cv2.IMREAD_GRAYSCALE),  (IMG_SIZE,IMG_SIZE))
            testing_data.append([np.array(img), img_num])

        np.save('test_data.npy', testing_data)
        return testing_data

    train_data = creat_train_data()
    #if you already have train data:
    #train_data = np.load('train_data.npy')
    100%|███████████████████████████████████████████████████████████████████████████| 21756/21756 [02:39<00:00, 136.07it/s]

    if os.path.exists('{}<.meta'.format(MODEL_NAME)):
        model.load(MODEL_NAME)
        print('model loaded!')

    train = train_data[:-500]
    test = train_data[:-500]

    X = np.array([i[0] for i in train]).reshape( -1, IMG_SIZE, IMG_SIZE, 1) #feature set
    Y= [i[1] for i in test] #label

    test_x = np.array([i[0] for i in train]).reshape( -1, IMG_SIZE, IMG_SIZE, 1) 
    test_y= [i[1] for i in test] 

    model.fit({'input': X}, {'targets': Y}, n_epoch=5, validation_set=({'input': test_x}, {'targets': test_y}), 
        snapshot_step=500, show_metric=True, run_id=MODEL_NAME)

    Training Step: 1664  | total loss: 9.55887 | time: 63.467s
    | Adam | epoch: 005 | loss: 9.55887 - acc: 0.5849 -- iter: 21248/21256
    Training Step: 1665  | total loss: 9.71830 | time: 74.722s
    | Adam | epoch: 005 | loss: 9.71830 - acc: 0.5779 | val_loss: 9.81653 - val_acc: 0.5737 -- iter: 21256/21256
    --

Three Questions

I have three issues which i have tried to solve, but i have had no luck finding solutions:

The first appears at: # Building convolutional convnet

    curses is not supported on this machine (please install/reinstall curses for an optimal experience)
    WARNING:tensorflow:From C:\Users\labadmin\Miniconda3\envs\tensorflow\lib\site-packages\tflearn\initializations.py:119: UniformUnitScaling.__init__ (from tensorflow.python.ops.init_ops) is deprecated and will be removed in a future version.
    Instructions for updating:
    Use tf.initializers.variance_scaling instead with distribution=uniform to get equivalent behavior.
    WARNING:tensorflow:From C:\Users\labadmin\Miniconda3\envs\tensorflow\lib\site-packages\tflearn\objectives.py:66: calling reduce_sum (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
    Instructions for updating:
    keep_dims is deprecated, use keepdims instead

The second appears at: print('model loaded!')

    if os.path.exists('{}<.meta'.format(MODEL_NAME)):
        model.load(MODEL_NAME)
        print('model loaded!')

Where the code does not print, does that mean that the data is not loaded?

The third

Tutorial does not go through how can i test my model with a image. So how and what can i add to code that take the model (which also is being saved), and run an image from my folder with the given output being the classification?

Solution

1st: the warning messages are clear, follow it and the warning will be gone. But don't worry, you still can run your code normally if you don't.

2nd: Yes. If the model load! is not printed out, the model is not loaded, check your path to the model file.

3rd: To save model after training, use model.save("PATH-TO-SAVE"). Then you can load it by model.load("PATH-TO-MODEL").

For prediction, use model.predict({'input': X}). See here http://tflearn.org/getting_started/#trainer-evaluator-predictor

2nd question

1. To save and load a model, use

# Save a model
model.save('path-to-folder-you-want-to-save/my_model.tflearn')
# Load a model
model.load('the-folder-where-your-model-located/my_model.tflearn')

remember that you should have the extension for the model file, which is .tflearn.

2. To predict, you need to load the image just like when you load it for training.

test_image = cv2.resize(cv2.imread("path-of-the-image", cv2.IMREAD_GRAYSCALE),  (IMG_SIZE,IMG_SIZE))

test_image = np.array(test_image).reshape( -1, IMG_SIZE, IMG_SIZE, 1)

prediction = model.predict({'input': test_image })

Answered By - Ha Bom