{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Dog Memorizer GAN\nIn this kernel we learn how to make a Dog Memorizer GAN. By publishing this kernel, it is my hope that Kaggle disallows Memorizer GANs from winning medals in this competition. Kagglers would like to invest time making complex Dog Generalizing GANs but they don't want to lose to a simple Dog Memorizing GAN. (This kernel is inspired by the tutorial [here][1] and by my previous kernels [here][2] and [here][3]).\n\n![image](http://playagricola.com/Kaggle/gan7419.png)\n\nA GAN consists of a Generator and Discriminator. After being trained, a Generator is a robot artist that draws dog images. During training the Discriminator teaches the Generator how to draw a dog. (And the G teaches the D also). The Generator never sees any images of dogs. Instead it continually attempts to draw a dog and is coached by the Discriminator. In this kernel, the **Memorizer** Generator is only coached to memorize images from the training set. In contrast, a **Generalizing** Generator is coached to draw images that have never existed nor been seen before!\n\n# Load and Crop Images\n\n[1]: https://medium.com/datadriveninvestor/generative-adversarial-network-gan-using-keras-ce1c05cfdfd3\n[2]: https://www.kaggle.com/cdeotte/dog-autoencoder\n[3]: https://www.kaggle.com/cdeotte/supervised-generative-dog-net"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"ComputeLB = False\nDogsOnly = False\n\nimport numpy as np, pandas as pd, os\nimport xml.etree.ElementTree as ET \nimport matplotlib.pyplot as plt, zipfile \nfrom PIL import Image \n\nROOT = '../input/generative-dog-images/'\nif not ComputeLB: ROOT = '../input/'\nIMAGES = os.listdir(ROOT + 'all-dogs/all-dogs/')\nbreeds = os.listdir(ROOT + 'annotation/Annotation/') \n\nidxIn = 0; namesIn = []\nimagesIn = np.zeros((25000,64,64,3))\n\n# CROP WITH BOUNDING BOXES TO GET DOGS ONLY\n# https://www.kaggle.com/paulorzp/show-annotations-and-breeds\nif DogsOnly:\n    for breed in breeds:\n        for dog in os.listdir(ROOT+'annotation/Annotation/'+breed):\n            try: img = Image.open(ROOT+'all-dogs/all-dogs/'+dog+'.jpg') \n            except: continue           \n            tree = ET.parse(ROOT+'annotation/Annotation/'+breed+'/'+dog)\n            root = tree.getroot()\n            objects = root.findall('object')\n            for o in objects:\n                bndbox = o.find('bndbox') \n                xmin = int(bndbox.find('xmin').text)\n                ymin = int(bndbox.find('ymin').text)\n                xmax = int(bndbox.find('xmax').text)\n                ymax = int(bndbox.find('ymax').text)\n                w = np.min((xmax - xmin, ymax - ymin))\n                img2 = img.crop((xmin, ymin, xmin+w, ymin+w))\n                img2 = img2.resize((64,64), Image.ANTIALIAS)\n                imagesIn[idxIn,:,:,:] = np.asarray(img2)\n                #if idxIn%1000==0: print(idxIn)\n                namesIn.append(breed)\n                idxIn += 1\n    idx = np.arange(idxIn)\n    np.random.shuffle(idx)\n    imagesIn = imagesIn[idx,:,:,:]\n    namesIn = np.array(namesIn)[idx]\n    \n# RANDOMLY CROP FULL IMAGES\nelse:\n    IMAGES = np.sort(IMAGES)\n    np.random.seed(810)\n    x = np.random.choice(np.arange(20579),10000)\n    np.random.seed(None)\n    for k in range(len(x)):\n        img = Image.open(ROOT + 'all-dogs/all-dogs/' + IMAGES[x[k]])\n        w = img.size[0]; h = img.size[1];\n        if (k%2==0)|(k%3==0):\n            w2 = 100; h2 = int(h/(w/100))\n            a = 18; b = 0          \n        else:\n            a=0; b=0\n            if w<h:\n                w2 = 64; h2 = int((64/w)*h)\n                b = (h2-64)//2\n            else:\n                h2 = 64; w2 = int((64/h)*w)\n                a = (w2-64)//2\n        img = img.resize((w2,h2), Image.ANTIALIAS)\n        img = img.crop((0+a, 0+b, 64+a, 64+b))    \n        imagesIn[idxIn,:,:,:] = np.asarray(img)\n        namesIn.append(IMAGES[x[k]])\n        #if idxIn%1000==0: print(idxIn)\n        idxIn += 1\n    \n# DISPLAY CROPPED IMAGES\nx = np.random.randint(0,idxIn,25)\nfor k in range(5):\n    plt.figure(figsize=(15,3))\n    for j in range(5):\n        plt.subplot(1,5,j+1)\n        img = Image.fromarray( imagesIn[x[k*5+j],:,:,:].astype('uint8') )\n        plt.axis('off')\n        if not DogsOnly: plt.title(namesIn[x[k*5+j]],fontsize=11)\n        else: plt.title(namesIn[x[k*5+j]].split('-')[1],fontsize=11)\n        plt.imshow(img)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"cell_type":"markdown","source":"# Build Discriminator"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Model\nfrom keras.layers import Input, Dense, Conv2D, Reshape, Flatten, concatenate\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import LearningRateScheduler\nfrom keras.optimizers import SGD, Adam","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# BUILD DISCRIMINATIVE NETWORK\ndog = Input((12288,))\ndogName = Input((10000,))\nx = Dense(12288, activation='sigmoid')(dogName) \nx = Reshape((2,12288,1))(concatenate([dog,x]))\nx = Conv2D(1,(2,1),use_bias=False,name='conv')(x)\ndiscriminated = Flatten()(x)\n\n# COMPILE\ndiscriminator = Model([dog,dogName], discriminated)\ndiscriminator.get_layer('conv').trainable = False\ndiscriminator.get_layer('conv').set_weights([np.array([[[[-1.0 ]]],[[[1.0]]]])])\ndiscriminator.compile(optimizer='adam', loss='binary_crossentropy')\n\n# DISPLAY ARCHITECTURE\ndiscriminator.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Train Discriminator\nWe will train the Discriminator to memorize the training images. (Typically you don't train the Discriminator ahead of time. The D learns as the G learns. But this GAN is special)."},{"metadata":{"trusted":true},"cell_type":"code","source":"# TRAINING DATA\ntrain_y = (imagesIn[:10000,:,:,:]/255.).reshape((-1,12288))\ntrain_X = np.zeros((10000,10000))\nfor i in range(10000): train_X[i,i] = 1\nzeros = np.zeros((10000,12288))\n\n# TRAIN NETWORK\nlr = 0.5\nfor k in range(5):\n    annealer = LearningRateScheduler(lambda x: lr)\n    h = discriminator.fit([zeros,train_X], train_y, epochs = 10, batch_size=256, callbacks=[annealer], verbose=0)\n    print('Epoch',(k+1)*10,'/30 - loss =',h.history['loss'][-1] )\n    if h.history['loss'][-1]<0.533: lr = 0.1","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Delete Training Images\nOur Discriminator has memorized all the training images. We will now delete the training images. Our Generator will never see the training images. It will only be coached by the Discriminator. Below are examples of images that the Discriminator memorized."},{"metadata":{"trusted":true},"cell_type":"code","source":"del train_X, train_y, imagesIn","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"print('Discriminator Recalls from Memory Dogs')    \nfor k in range(5):\n    plt.figure(figsize=(15,3))\n    for j in range(5):\n        xx = np.zeros((10000))\n        xx[np.random.randint(10000)] = 1\n        plt.subplot(1,5,j+1)\n        img = discriminator.predict([zeros[0,:].reshape((-1,12288)),xx.reshape((-1,10000))]).reshape((-1,64,64,3))\n        img = Image.fromarray( (255*img).astype('uint8').reshape((64,64,3)))\n        plt.axis('off')\n        plt.imshow(img)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Build Generator and GAN"},{"metadata":{"trusted":true},"cell_type":"code","source":"# BUILD GENERATOR NETWORK\nseed = Input((10000,))\ngenerated = Dense(12288, activation='linear')(seed)\n\n# COMPILE\ngenerator = Model(seed, [generated,Reshape((10000,))(seed)])\n\n# DISPLAY ARCHITECTURE\ngenerator.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# BUILD GENERATIVE ADVERSARIAL NETWORK\ndiscriminator.trainable=False    \ngan_input = Input(shape=(10000,))\nx = generator(gan_input)\ngan_output = discriminator(x)\n\n# COMPILE GAN\ngan = Model(gan_input, gan_output)\ngan.get_layer('model_1').get_layer('conv').set_weights([np.array([[[[-1 ]]],[[[255.]]]])])\ngan.compile(optimizer=Adam(5), loss='mean_squared_error')\n\n# DISPLAY ARCHITECTURE\ngan.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Discriminator Coaches Generator\nIn a typical GAN, the discriminator does not memorize the training images beforehand. Instead it learns to distinquish real images from fake images at the same time that the Generator learns to make fake images. In this GAN, we taught the Discriminator ahead of time and it will now teach the Generator."},{"metadata":{"trusted":true},"cell_type":"code","source":"# TRAINING DATA\ntrain = np.zeros((10000,10000))\nfor i in range(10000): train[i,i] = 1\nzeros = np.zeros((10000,12288))\n\n# TRAIN NETWORKS\nlr = 5.\nfor k in range(50):  \n\n    # BEGIN DISCRIMINATOR COACHES GENERATOR\n    annealer = LearningRateScheduler(lambda x: lr)\n    h = gan.fit(train, zeros, epochs = 1, batch_size=256, callbacks=[annealer], verbose=0)\n    if (k<10)|(k%5==4):\n        print('Epoch',(k+1)*10,'/500 - loss =',h.history['loss'][-1] )\n    if h.history['loss'][-1] < 25: lr = 1.\n    if h.history['loss'][-1] < 1.5: lr = 0.5\n        \n    # DISPLAY GENERATOR LEARNING PROGRESS\n    if k<10:        \n        plt.figure(figsize=(15,3))\n        for j in range(5):\n            xx = np.zeros((10000))\n            xx[np.random.randint(10000)] = 1\n            plt.subplot(1,5,j+1)\n            img = generator.predict(xx.reshape((-1,10000)))[0].reshape((-1,64,64,3))\n            img = Image.fromarray( (img).astype('uint8').reshape((64,64,3)))\n            plt.axis('off')\n            plt.imshow(img)\n        plt.show()  ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Build Generator Class\nOur Generative Network has now learned all the training images from our Discriminative Network. We would like our Dog Generator to accept any random 100 dimensional vector and output an image. Furthermore we need to slightly perturb each memorized image so we don't submit exact copies of training images. Let's build a Generator Class"},{"metadata":{"trusted":true},"cell_type":"code","source":"class DogGenerator:\n    index = 0   \n    def getDog(self,seed):\n        xx = np.zeros((10000))\n        xx[self.index] = 0.999\n        xx[np.random.randint(10000)] = 0.001\n        img = generator.predict(xx.reshape((-1,10000)))[0].reshape((64,64,3))\n        self.index = (self.index+1)%10000\n        return Image.fromarray( img.astype('uint8') ) ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Suggestion to Kaggle Judges\nIn my opinion, **Memorizer** GANs should be disallowed from winning prizes in Kaggle's \"Generating Dog Images\" competition. This kernel serves as an example of a GAN which accepts any random vector of length 100 and returns a dog image that does not exist in the training dataset. However I believe that this solution isn't what this research competition is looking for.\n\nOne can detect **Memorizer** GANs by their limited valid image output count. This GAN only outputs 10000 good images. A **Generalizing** GAN should output millions of images. Kaggle judges can verify the variety of outputted images by randomly selecting 10000 seeds (of their choice) and inputting them into a participant's GAN. Then compare those images' score to private LB score. (Each participant could provide a `DogGenerator` Class).\n\nThis kernel would pass the above test so additionally you must test for variety and generalization by choosing 2 random seeds in latent space and interpolating 100 seeds inbetween. Then convert each seed into an image. A **Generalizing** GAN should output 100 unique images that smoothly transist one to the next. And all of them should be interesting valid dog pictures. More info about latent walking [here][1]\n\n[1]: https://www.kaggle.com/cdeotte/supervised-generative-dog-net"},{"metadata":{},"cell_type":"markdown","source":"# Submit to Kaggle\nMy hope is that Kaggle disallows **Memorizer** GANs from winning medals in this competition. The purpose of submitting this high scoring kernel is to demonstrate that it is too easy to achieve a high score with a simple **Memorizer** GAN. The more complex and interesting solutions are **Generalizing** GANs!"},{"metadata":{"trusted":true},"cell_type":"code","source":"# SAVE TO ZIP FILE NAMED IMAGES.ZIP\nz = zipfile.PyZipFile('images.zip', mode='w')\nd = DogGenerator()\nfor k in range(10000):\n    img = d.getDog(np.random.normal(0,1,100))\n    f = str(k)+'.png'\n    img.save(f,'PNG'); z.write(f); os.remove(f)\n    #if k % 1000==0: print(k)\nz.close()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Calculate LB Score\nIf you wish to compute LB, you must add the LB metric dataset [here][1] to this kernel and change the boolean variable in the first cell block.\n\n[1]: https://www.kaggle.com/wendykan/dog-face-generation-competition-kid-metric-input"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"from __future__ import absolute_import, division, print_function\nimport numpy as np\nimport os\nimport gzip, pickle\nimport tensorflow as tf\nfrom scipy import linalg\nimport pathlib\nimport urllib\nimport warnings\nfrom tqdm import tqdm\nfrom PIL import Image\n\nclass KernelEvalException(Exception):\n    pass\n\nmodel_params = {\n    'Inception': {\n        'name': 'Inception', \n        'imsize': 64,\n        'output_layer': 'Pretrained_Net/pool_3:0', \n        'input_layer': 'Pretrained_Net/ExpandDims:0',\n        'output_shape': 2048,\n        'cosine_distance_eps': 0.1\n        }\n}\n\ndef create_model_graph(pth):\n    \"\"\"Creates a graph from saved GraphDef file.\"\"\"\n    # Creates graph from saved graph_def.pb.\n    with tf.gfile.FastGFile( pth, 'rb') as f:\n        graph_def = tf.GraphDef()\n        graph_def.ParseFromString( f.read())\n        _ = tf.import_graph_def( graph_def, name='Pretrained_Net')\n\ndef _get_model_layer(sess, model_name):\n    # layername = 'Pretrained_Net/final_layer/Mean:0'\n    layername = model_params[model_name]['output_layer']\n    layer = sess.graph.get_tensor_by_name(layername)\n    ops = layer.graph.get_operations()\n    for op_idx, op in enumerate(ops):\n        for o in op.outputs:\n            shape = o.get_shape()\n            if shape._dims != []:\n              shape = [s.value for s in shape]\n              new_shape = []\n              for j, s in enumerate(shape):\n                if s == 1 and j == 0:\n                  new_shape.append(None)\n                else:\n                  new_shape.append(s)\n              o.__dict__['_shape_val'] = tf.TensorShape(new_shape)\n    return layer\n\ndef get_activations(images, sess, model_name, batch_size=50, verbose=False):\n    \"\"\"Calculates the activations of the pool_3 layer for all images.\n\n    Params:\n    -- images      : Numpy array of dimension (n_images, hi, wi, 3). The values\n                     must lie between 0 and 256.\n    -- sess        : current session\n    -- batch_size  : the images numpy array is split into batches with batch size\n                     batch_size. A reasonable batch size depends on the disposable hardware.\n    -- verbose    : If set to True and parameter out_step is given, the number of calculated\n                     batches is reported.\n    Returns:\n    -- A numpy array of dimension (num images, 2048) that contains the\n       activations of the given tensor when feeding inception with the query tensor.\n    \"\"\"\n    inception_layer = _get_model_layer(sess, model_name)\n    n_images = images.shape[0]\n    if batch_size > n_images:\n        print(\"warning: batch size is bigger than the data size. setting batch size to data size\")\n        batch_size = n_images\n    n_batches = n_images//batch_size + 1\n    pred_arr = np.empty((n_images,model_params[model_name]['output_shape']))\n    for i in tqdm(range(n_batches)):\n        if verbose:\n            print(\"\\rPropagating batch %d/%d\" % (i+1, n_batches), end=\"\", flush=True)\n        start = i*batch_size\n        if start+batch_size < n_images:\n            end = start+batch_size\n        else:\n            end = n_images\n                    \n        batch = images[start:end]\n        pred = sess.run(inception_layer, {model_params[model_name]['input_layer']: batch})\n        pred_arr[start:end] = pred.reshape(-1,model_params[model_name]['output_shape'])\n    if verbose:\n        print(\" done\")\n    return pred_arr\n\n\n# def calculate_memorization_distance(features1, features2):\n#     neigh = NearestNeighbors(n_neighbors=1, algorithm='kd_tree', metric='euclidean')\n#     neigh.fit(features2) \n#     d, _ = neigh.kneighbors(features1, return_distance=True)\n#     print('d.shape=',d.shape)\n#     return np.mean(d)\n\ndef normalize_rows(x: np.ndarray):\n    \"\"\"\n    function that normalizes each row of the matrix x to have unit length.\n\n    Args:\n     ``x``: A numpy matrix of shape (n, m)\n\n    Returns:\n     ``x``: The normalized (by row) numpy matrix.\n    \"\"\"\n    return np.nan_to_num(x/np.linalg.norm(x, ord=2, axis=1, keepdims=True))\n\n\ndef cosine_distance(features1, features2):\n    # print('rows of zeros in features1 = ',sum(np.sum(features1, axis=1) == 0))\n    # print('rows of zeros in features2 = ',sum(np.sum(features2, axis=1) == 0))\n    features1_nozero = features1[np.sum(features1, axis=1) != 0]\n    features2_nozero = features2[np.sum(features2, axis=1) != 0]\n    norm_f1 = normalize_rows(features1_nozero)\n    norm_f2 = normalize_rows(features2_nozero)\n\n    d = 1.0-np.abs(np.matmul(norm_f1, norm_f2.T))\n    print('d.shape=',d.shape)\n    print('np.min(d, axis=1).shape=',np.min(d, axis=1).shape)\n    mean_min_d = np.mean(np.min(d, axis=1))\n    print('distance=',mean_min_d)\n    return mean_min_d\n\n\ndef distance_thresholding(d, eps):\n    if d < eps:\n        return d\n    else:\n        return 1\n\ndef calculate_frechet_distance(mu1, sigma1, mu2, sigma2, eps=1e-6):\n    \"\"\"Numpy implementation of the Frechet Distance.\n    The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1)\n    and X_2 ~ N(mu_2, C_2) is\n            d^2 = ||mu_1 - mu_2||^2 + Tr(C_1 + C_2 - 2*sqrt(C_1*C_2)).\n            \n    Stable version by Dougal J. Sutherland.\n\n    Params:\n    -- mu1 : Numpy array containing the activations of the pool_3 layer of the\n             inception net ( like returned by the function 'get_predictions')\n             for generated samples.\n    -- mu2   : The sample mean over activations of the pool_3 layer, precalcualted\n               on an representive data set.\n    -- sigma1: The covariance matrix over activations of the pool_3 layer for\n               generated samples.\n    -- sigma2: The covariance matrix over activations of the pool_3 layer,\n               precalcualted on an representive data set.\n\n    Returns:\n    --   : The Frechet Distance.\n    \"\"\"\n\n    mu1 = np.atleast_1d(mu1)\n    mu2 = np.atleast_1d(mu2)\n\n    sigma1 = np.atleast_2d(sigma1)\n    sigma2 = np.atleast_2d(sigma2)\n\n    assert mu1.shape == mu2.shape, \"Training and test mean vectors have different lengths\"\n    assert sigma1.shape == sigma2.shape, \"Training and test covariances have different dimensions\"\n\n    diff = mu1 - mu2\n\n    # product might be almost singular\n    covmean, _ = linalg.sqrtm(sigma1.dot(sigma2), disp=False)\n    if not np.isfinite(covmean).all():\n        msg = \"fid calculation produces singular product; adding %s to diagonal of cov estimates\" % eps\n        warnings.warn(msg)\n        offset = np.eye(sigma1.shape[0]) * eps\n        # covmean = linalg.sqrtm((sigma1 + offset).dot(sigma2 + offset))\n        covmean = linalg.sqrtm((sigma1 + offset).dot(sigma2 + offset))\n    \n    # numerical error might give slight imaginary component\n    if np.iscomplexobj(covmean):\n        if not np.allclose(np.diagonal(covmean).imag, 0, atol=1e-3):\n            m = np.max(np.abs(covmean.imag))\n            raise ValueError(\"Imaginary component {}\".format(m))\n        covmean = covmean.real\n\n    # covmean = tf.linalg.sqrtm(tf.linalg.matmul(sigma1,sigma2))\n\n    print('covmean.shape=',covmean.shape)\n    # tr_covmean = tf.linalg.trace(covmean)\n\n    tr_covmean = np.trace(covmean)\n    return diff.dot(diff) + np.trace(sigma1) + np.trace(sigma2) - 2 * tr_covmean\n    # return diff.dot(diff) + tf.linalg.trace(sigma1) + tf.linalg.trace(sigma2) - 2 * tr_covmean\n#-------------------------------------------------------------------------------\n\n\ndef calculate_activation_statistics(images, sess, model_name, batch_size=50, verbose=False):\n    \"\"\"Calculation of the statistics used by the FID.\n    Params:\n    -- images      : Numpy array of dimension (n_images, hi, wi, 3). The values\n                     must lie between 0 and 255.\n    -- sess        : current session\n    -- batch_size  : the images numpy array is split into batches with batch size\n                     batch_size. A reasonable batch size depends on the available hardware.\n    -- verbose     : If set to True and parameter out_step is given, the number of calculated\n                     batches is reported.\n    Returns:\n    -- mu    : The mean over samples of the activations of the pool_3 layer of\n               the incption model.\n    -- sigma : The covariance matrix of the activations of the pool_3 layer of\n               the incption model.\n    \"\"\"\n    act = get_activations(images, sess, model_name, batch_size, verbose)\n    mu = np.mean(act, axis=0)\n    sigma = np.cov(act, rowvar=False)\n    return mu, sigma, act\n    \ndef _handle_path_memorization(path, sess, model_name, is_checksize, is_check_png):\n    path = pathlib.Path(path)\n    files = list(path.glob('*.jpg')) + list(path.glob('*.png'))\n    imsize = model_params[model_name]['imsize']\n\n    # In production we don't resize input images. This is just for demo purpose. \n    x = np.array([np.array(img_read_checks(fn, imsize, is_checksize, imsize, is_check_png)) for fn in files])\n    m, s, features = calculate_activation_statistics(x, sess, model_name)\n    del x #clean up memory\n    return m, s, features\n\n# check for image size\ndef img_read_checks(filename, resize_to, is_checksize=False, check_imsize = 64, is_check_png = False):\n    im = Image.open(str(filename))\n    if is_checksize and im.size != (check_imsize,check_imsize):\n        raise KernelEvalException('The images are not of size '+str(check_imsize))\n    \n    if is_check_png and im.format != 'PNG':\n        raise KernelEvalException('Only PNG images should be submitted.')\n\n    if resize_to is None:\n        return im\n    else:\n        return im.resize((resize_to,resize_to),Image.ANTIALIAS)\n\ndef calculate_kid_given_paths(paths, model_name, model_path, feature_path=None, mm=[], ss=[], ff=[]):\n    ''' Calculates the KID of two paths. '''\n    tf.reset_default_graph()\n    create_model_graph(str(model_path))\n    with tf.Session() as sess:\n        sess.run(tf.global_variables_initializer())\n        m1, s1, features1 = _handle_path_memorization(paths[0], sess, model_name, is_checksize = True, is_check_png = True)\n        if len(mm) != 0:\n            m2 = mm\n            s2 = ss\n            features2 = ff\n        elif feature_path is None:\n            m2, s2, features2 = _handle_path_memorization(paths[1], sess, model_name, is_checksize = False, is_check_png = False)\n        else:\n            with np.load(feature_path) as f:\n                m2, s2, features2 = f['m'], f['s'], f['features']\n\n        print('m1,m2 shape=',(m1.shape,m2.shape),'s1,s2=',(s1.shape,s2.shape))\n        print('starting calculating FID')\n        fid_value = calculate_frechet_distance(m1, s1, m2, s2)\n        print('done with FID, starting distance calculation')\n        distance = cosine_distance(features1, features2)        \n        return fid_value, distance, m2, s2, features2","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"if ComputeLB:\n  \n    # UNCOMPRESS OUR IMGAES\n    with zipfile.ZipFile(\"../working/images.zip\",\"r\") as z:\n        z.extractall(\"../tmp/images2/\")\n\n    # COMPUTE LB SCORE\n    m2 = []; s2 =[]; f2 = []\n    user_images_unzipped_path = '../tmp/images2/'\n    images_path = [user_images_unzipped_path,'../input/generative-dog-images/all-dogs/all-dogs/']\n    public_path = '../input/dog-face-generation-competition-kid-metric-input/classify_image_graph_def.pb'\n\n    fid_epsilon = 10e-15\n\n    fid_value_public, distance_public, m2, s2, f2 = calculate_kid_given_paths(images_path, 'Inception', public_path, mm=m2, ss=s2, ff=f2)\n    distance_public = distance_thresholding(distance_public, model_params['Inception']['cosine_distance_eps'])\n    print(\"FID_public: \", fid_value_public, \"distance_public: \", distance_public, \"multiplied_public: \",\n            fid_value_public /(distance_public + fid_epsilon))\n    \n    # REMOVE FILES TO PREVENT KERNEL ERROR OF TOO MANY FILES\n    ! rm -r ../tmp","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}