'xavier_initializer' not supported, please update TensorFlow - tensorflow

I use google-colab
My function is:
def createModelUsingTensorflow(nbClasses, imageSizeX, imageSizeY, imageSizeZ, args):
'''Create the Deep Neural Network Model'''
print("[+] Creating model...")
convnet = input_data(shape=[None, imageSizeX, imageSizeY, imageSizeZ], name='input')
convnet = conv_2d(convnet, 64, 2, activation='relu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 2, activation='relu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 256, 2, activation='relu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 512, 2, activation='relu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 1024, 2, activation='relu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 2048, 2, activation='relu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = fully_connected(convnet, 4096, activation='relu')
convnet = dropout(convnet, 0.5)
convnet = fully_connected(convnet, nbClasses, activation='softmax')
convnet = regression(convnet, optimizer='adam', loss='categorical_crossentropy', learning_rate=learningRate)
# model = tflearn.DNN(convnet, tensorboard_dir='tensorboard', tensorboard_verbose=3)
createFolder(checkpointPath)
model = tflearn.DNN(convnet, checkpoint_path='{}/model.tfl'.format(checkpointPath), max_checkpoints=1)
if args.resume and args.epochs:
try:
model.load('{}/model.tfl-{}'.format(checkpointPath, args.resume))
print(" Model retrieved and resuming training!")
except Exception as err:
print("Couldn't load the previous model", err)
raise err
else:
print(" Model created!")
return model
I get an error when I call the function
My error is:
enter image description here
because the version of the TensorFlow
What can I do ? or How do I use Glorot in my function?
thanks!!

From the image you shared, it seems you are using tflearn library instead of Tensorflow or Keras. In that case, you will have to pass tflearn.initializations.xavier() method to weights_init= in your conv_2d call.
The method signature for tflearn.initializations.xavier() is:
tflearn.initializations.xavier (uniform=True, seed=None, dtype=tf.float32)
Hope that works!
P.S: A small suggestion, always share your relevant import statements or proper library name and version for people to help you better and quicker

Related

how can i build tensorflow model in specific shape?

BATCH_SIZE = 32 # ADVISED NOT TO CHANGE THIS
N_PAST = 10 # DO NOT CHANGE THIS
N_FUTURE = 10 # DO NOT CHANGE THIS
SHIFT = 1
model = tf.keras.models.Sequential([
tf.keras.layers.Conv1D(filters=32, kernel_size=5,
strides=1, padding="causal",
activation="relu",
input_shape=[None, 1]),
tf.keras.layers.LSTM(64, return_sequences=True),
tf.keras.layers.LSTM(64, return_sequences=True),
tf.keras.layers.Dense(30, activation="relu"),
tf.keras.layers.Dense(10, activation="relu"),
tf.keras.layers.Dense(N_FEATURES)
])
I build a time-siries forcasting model but i can't understand how to handle this.
which layer should i use to make this available?
Model input shape must be (BATCH_SIZE, N_PAST = 10, N_FEATURES = 1)
Model output shape must be (BATCH_SIZE, N_FUTURE = 10, N_FEATURES = 1)
the batch_size is not specified in the model.
model = tf.keras.models.Sequential([
tf.keras.layers.Conv1D(filters=32, kernel_size=5,
strides=1, padding="causal",
activation="relu",
input_shape=[N_PAST,1]),
tf.keras.layers.LSTM(64, return_sequences=True),
tf.keras.layers.Dense(30, activation="relu"),
tf.keras.layers.Dense(10, activation="relu"),
tf.keras.layers.Dense(N_FUTURE)
])
You don't need to specify batch_size in input layer. Just change input shape as follows:
input_shape=[N_PAST,1]

GAN with batch norm acting very weird, both discriminator and generator get zero loss

I am training a DCGAN model with tensorflow.keras, and I added BatchNormalization layers in both generator and discriminator.
I train gan with following steps:
1. train discriminator with real images and images from generator(using generator.predict)
2. train adversarial network(compiled with discriminator.trainable=False)
Then I found that after a few rounds the training loss returned by train_on_batch() of both generator and discriminator goes to zero. But when I use test_on_batch() the loss is still huge for generator. And the generated images are all mess.
At first I thought that it is because in the 2.'s step mentioned above when training the adversarial network, the discriminator's input only containing fake images makes the batch normalization layers get different distribution as the 1.'s step when both fake & real images were fed.
But even if I removed all batch normalization layers in discriminator, the same problem still exists. Only when all batch normalization layers were removed the problem will disappear. Also I found out that existences of Dropout layers don't make a difference. I wondering why batch normalization can cause such problem, even if in generator fed with noises with same distribution.
# Model definition
class DCGAN_128:
def __init__(self, hidden_dim):
generator = M.Sequential()
generator.add(L.Dense(128 * 8 * 8, input_shape=[hidden_dim]))
generator.add(L.Reshape([8, 8, 128]))
generator.add(L.UpSampling2D()) # [8, 8, 128]
generator.add(L.Conv2D(128, kernel_size=3, padding="same")) # [16, 16, 128]
generator.add(L.LayerNormalization()) # 4
generator.add(L.ReLU())
generator.add(L.UpSampling2D()) # [32, 32, 128]
generator.add(L.Conv2D(64, kernel_size=5, padding="same")) # [32, 32, 64]
generator.add(L.LayerNormalization()) # 8
generator.add(L.ReLU())
generator.add(L.UpSampling2D()) # [64, 64, 128]
generator.add(L.Conv2D(32, kernel_size=7, padding="same")) # [64, 64, 32]
generator.add(L.LayerNormalization()) # 12
generator.add(L.ReLU())
generator.add(L.UpSampling2D()) # [128, 128, 32]
generator.add(L.Conv2D(3, kernel_size=3, padding="same", activation=A.sigmoid)) # [128, 128, 3]
discriminator = M.Sequential()
discriminator.add(L.Conv2D(32, kernel_size=5, strides=2, padding="same", input_shape=[128, 128, 3]))
discriminator.add(L.LeakyReLU())
# discriminator.add(L.Dropout(0.25)) # [64, 64, 32]
discriminator.add(L.Conv2D(64, kernel_size=3, strides=2, padding="same"))
# discriminator.add(L.BatchNormalization(epsilon=1e-5)) # 4
discriminator.add(L.LeakyReLU())
# discriminator.add(L.Dropout(0.25)) # [32, 32, 64]
discriminator.add(L.Conv2D(128, kernel_size=3, strides=2, padding="same"))
discriminator.add(L.LayerNormalization()) # 8
discriminator.add(L.LeakyReLU()) # [16, 16, 128]
discriminator.add(L.Dropout(0.25))
discriminator.add(L.Conv2D(256, kernel_size=3, strides=2, padding="same"))
discriminator.add(L.LayerNormalization()) # 12
discriminator.add(L.LeakyReLU()) # [8, 8, 256]
discriminator.add(L.Dropout(0.25))
discriminator.add(L.Conv2D(512, kernel_size=3, strides=2, padding="same"))
discriminator.add(L.LeakyReLU()) # [4, 4, 512]
discriminator.add(L.Flatten())
discriminator.add(L.Dense(1, activation=A.sigmoid))
self.model_gen = generator
self.model_dis = discriminator
self.adv_input = L.Input([hidden_dim])
self.adv_output = discriminator(generator(self.adv_input))
self.model_adversarial = M.Model(self.adv_input, self.adv_output)
# Training
dcgan = hidden_dim = 100
DCGAN_128(hidden_dim)
data_loader = AnimeFacesLoader([128, 128])
batch_size = 32
n_rounds = 40000
dis_model = dcgan.model_dis
gen_model = dcgan.model_gen
adv_model = dcgan.model_adversarial
gen_model.summary()
adv_model.summary()
dis_model.compile(Opt.Adam(0.0002), Lo.binary_crossentropy)
dis_model.trainable = False
adv_model.compile(Opt.Adam(0.0002), Lo.binary_crossentropy)
layer_outputs = [layer.output for layer in dis_model.layers]
visual_model = tf.keras.Model(dis_model.input, layer_outputs)
for rounds in range(n_rounds):
# Get output images
if rounds % 100 == 0 and rounds > 0:
noise = np.random.uniform(-1, 1, [16, hidden_dim])
tiled_images = np.zeros([4*128, 4*128, 3]).astype(np.uint8)
generated_imgs = gen_model.predict(noise)
generated_imgs *= 256
generated_imgs = generated_imgs.astype(np.uint8)
for i in range(16):
tiled_images[int(i / 4)*128: int(i / 4)*128 + 128,
int(i % 4)*128: int(i % 4)*128 + 128, :] = generated_imgs[i, :, :, :]
Image.fromarray(tiled_images).save("Output/DCGAN/" + "rounds_{0}.jpg".format(rounds))
'''
layer_visualization = visual_model.predict(generated_imgs[:1])
for i in range(len(layer_visualization)):
plt.imshow(layer_visualization[i][0, :, :, 0])
plt.show()
'''
# train discriminator on real & fake images
real_imgs = data_loader.get_batch(batch_size)
real_ys = np.ones([batch_size, 1])
noise = np.random.uniform(-1, 1, [batch_size, hidden_dim])
fake_ys = np.zeros([batch_size, 1])
fake_imgs = gen_model.predict(noise)
imgs = np.concatenate([real_imgs, fake_imgs], axis=0)
ys = np.concatenate([real_ys, fake_ys], axis=0)
loss_dis = dis_model.train_on_batch(imgs, ys)
print("Round {}, Loss dis:{:.4f}".format(rounds, loss_dis))
loss_dis_test = dis_model.test_on_batch(imgs, ys)
print(loss_dis_test)
noise = np.random.uniform(-1, 1, [batch_size, hidden_dim])
fake_ys = np.ones([batch_size, 1])
loss_gen = adv_model.train_on_batch(noise, fake_ys)
print("Round {}, Loss gen:{:.4f}".format(rounds, loss_gen))
loss_gen_test = adv_model.test_on_batch(noise, fake_ys)
print(loss_gen_test)

How to prune weights in Tensorflow CNN model (Without migrating model to Keras)

I have a TF CNN model and now I want to use the weight pruning API of tensor flow with this but all the examples I checked online, it works only with Keras model
I want to prune wights of my existing model
def mnist_cnn(inputs):
input_layer = tf.reshape(inputs, [-1, 28, 28, 3])
# Convolutional Layer #1
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=32,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #1
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
# Convolutional Layer #2 and Pooling Layer #2
conv2 = tf.layers.conv2d(
inputs=pool1,
filters=64,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
# Dense Layer
pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])
dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
dropout = tf.layers.dropout(inputs=dense, rate=0.4)
# Logits Layer
outputs = tf.layers.dense(inputs=dropout, units=10)
return outputs
This tutorial defines weight pruning
https://www.tensorflow.org/model_optimization/guide/pruning/pruning_with_keras
but I can't figure out how to use Pruning APIs with my exiting model ( without upgrading it to keras sequential model )

Image regression with CNN

My immediate problem is that all of the various CNN regression models I've tried always return the same (or very similar) values and I'm trying to figure out why. But I would be open to a wide range of suggestions.
My dataset looks like this:
x: 64x64 greyscale images arranged into a 64 x 64 x n ndarray
y: Values between 0 and 1, each corresponding to an image (think of this as some sort of proportion)
weather: 4 weather readings from the time each image was taken (ambient temperature, humidity, dewpoint, air pressure)
The goal is to use the images and weather data to predict y. Since I'm working with images, I thought a CNN would be appropriate (please let me know if there are other strategies here).
From what I understand, CNNs are most often used for classification tasks--it's rather unusual to use them for regression. But in theory, it shouldn't be too different--I just need to change the loss function to MSE/RMSE and the last activation function to linear (although maybe a sigmoid is more appropriate here since y is between 0 and 1).
The first hurdle I ran into was trying to figure out how to incorporate the weather data, and the natural choice was to incorporate them into the first fully connected layer. I found an example here: How to train mix of image and data in CNN using ImageAugmentation in TFlearn
The second hurdle I ran into was determining an architecture. Normally I would just pick a paper and copy its architecture, but I couldn't find anything on CNN image regression. So I tried a (fairly simple) network with 3 convolutional layers and 2 fully connected layers, then I tried VGGNet and AlexNet architectures from https://github.com/tflearn/tflearn/tree/master/examples
Now the problem I'm having is that all of the models I'm trying output the same value, namely the mean y of the training set. Looking at tensorboard, the loss function flattens out fairly quickly (after around 25 epochs). Do you know what's going on here? While I do understand the basics of what each layer is doing, I have no intuition on what makes a good architecture for a particular dataset or task.
Here is an example. I am using VGGNet from the tflearn examples page:
tf.reset_default_graph()
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_flip_updown()
img_aug.add_random_90degrees_rotation(rotations=[0, 1, 2, 3])
convnet = input_data(shape=[None, size, size, 1],
data_augmentation=img_aug,
name='hive')
weathernet = input_data(shape=[None, 4], name='weather')
convnet = conv_2d(convnet, 64, 3, activation='relu', scope='conv1_1')
convnet = conv_2d(convnet, 64, 3, activation='relu', scope='conv1_2')
convnet = max_pool_2d(convnet, 2, strides=2, name='maxpool1')
convnet = conv_2d(convnet, 128, 3, activation='relu', scope='conv2_1')
convnet = conv_2d(convnet, 128, 3, activation='relu', scope='conv2_2')
convnet = max_pool_2d(convnet, 2, strides=2, name='maxpool2')
convnet = conv_2d(convnet, 256, 3, activation='relu', scope='conv3_1')
convnet = conv_2d(convnet, 256, 3, activation='relu', scope='conv3_2')
convnet = conv_2d(convnet, 256, 3, activation='relu', scope='conv3_3')
convnet = max_pool_2d(convnet, 2, strides=2, name='maxpool3')
convnet = conv_2d(convnet, 512, 3, activation='relu', scope='conv4_1')
convnet = conv_2d(convnet, 512, 3, activation='relu', scope='conv4_2')
convnet = conv_2d(convnet, 512, 3, activation='relu', scope='conv4_3')
convnet = max_pool_2d(convnet, 2, strides=2, name='maxpool4')
convnet = conv_2d(convnet, 512, 3, activation='relu', scope='conv5_1')
convnet = conv_2d(convnet, 512, 3, activation='relu', scope='conv5_2')
convnet = conv_2d(convnet, 512, 3, activation='relu', scope='conv5_3')
convnet = max_pool_2d(convnet, 2, strides=2, name='maxpool5')
convnet = fully_connected(convnet, 4096, activation='relu', scope='fc6')
convnet = merge([convnet, weathernet], 'concat')
convnet = dropout(convnet, .75, name='dropout1')
convnet = fully_connected(convnet, 4096, activation='relu', scope='fc7')
convnet = dropout(convnet, .75, name='dropout2')
convnet = fully_connected(convnet, 1, activation='sigmoid', scope='fc8')
convnet = regression(convnet,
optimizer='adam',
learning_rate=learning_rate,
loss='mean_square',
name='targets')
model = tflearn.DNN(convnet,
tensorboard_dir='log',
tensorboard_verbose=0)
model.fit({
'hive': x_train,
'weather': weather_train
},
{'targets': y_train},
n_epoch=1000,
batch_size=batch_size,
validation_set=({
'hive': x_val,
'weather': weather_val
},
{'targets': y_val}),
show_metric=False,
shuffle=True,
run_id='poop')
To get at what my objects are:
x_train is an ndarray of shape (n, 64, 64, 1)
weather_train is an ndarray of shape (n, 4)
y_train is an ndarray of shape (n, 1)
Overfitting is another concern, but given that the models perform poorly on the training set, I think I can worry about that later.
To address your concern regarding the same predicted value for all instances in your test set. You have a couple options here that don't involve changing the structure of your conv net:
You can rescale your target variable using sklearn StandardScaler() (which standardizes features by removing the mean and scaling to unit variance)
Scale pixel data; generally performance increases with scaled pixel data, as a rule of thumb always divide pixel data by 255.0 (shown at end of post)
You can play around with learning rate and the error function (the reason that the CNN is outputting the same value for all predictions is because that is what it has determined is the point of minimum error)
Next. If you are trying to perform regression ensure that your final fully connected layer uses a linear activation function instead of sigmoid. A linear activation function takes inputs to the neuron multiplied by the neuron weight and creates an output proportional to the input.
convnet = fully_connected(convnet, 1, activation='linear', scope='fc8')
Lastly. I have recently implemented ResNet50 for regression tasks in Keras. Here is the construction of that network, this version does not permit loading of pretrained weights and it must receive images of shape (224, 224, 3).
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import Conv2D, MaxPooling2D, DepthwiseConv2D
from keras.layers.core import Activation, Dropout, Dense
from keras.layers import Flatten, Input, Add, ZeroPadding2D, GlobalAveragePooling2D, GlobalMaxPooling2D
from keras.models import Model
from keras import backend
def block1(x, filters, kernel_size=3, stride=1, conv_shortcut=True, name=None):
"""
A residual block
:param x: input tensor
:param filters: integer, filters of the bottleneck layer
:param kernel_size: kernel size of bottleneck
:param stride: stride of first layer
:param conv_shortcut: use convolution shortcut if true, otherwise identity shortcut
:param name: string, block label
:return: Output tensor of the residual block
"""
# bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1
bn_axis = -1
if conv_shortcut is True:
shortcut = Conv2D(4 * filters, 1, strides=stride, name=name+'_0_conv')(x)
shortcut = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name=name+'_0_bn')(shortcut)
else:
shortcut = x
x = Conv2D(filters, 1, strides=stride, name=name+'_1_conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name=name+'_1_bn')(x)
x = Activation('relu', name=name+'_1_relu')(x)
x = Conv2D(filters, kernel_size, padding='SAME', name=name+'_2_conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name=name+'_2_bn')(x)
x = Activation('relu', name=name+'_2_relu')(x)
x = Conv2D(4 * filters, 1, name=name+'_3_conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name=name+'_3_bn')(x)
x = Add(name=name+'_add')([shortcut, x])
x = Activation('relu', name=name+'_out')(x)
return x
def stack1(x, filters, blocks, stride1=2, name=None):
"""
a set of stacked residual blocks
:param x: input tensor
:param filters: int, filters fof the bottleneck layer in the block
:param blocks: int, blocks in the stacked blocks,
:param stride1: stride of the first layer in the first block
:param name: stack label
:return: output tensor for the stacked blocks
"""
x = block1(x, filters, stride=stride1, name=name+'_block1')
for i in range(2, blocks+1):
x = block1(x, filters, conv_shortcut=False, name=name+'_block'+str(i))
return x
def resnet(height, width, depth, stack_fn, use_bias=False, nodes=256):
"""
:param height: height of image, int
:param width: image width, int
:param depth: bn_axis or depth, int
:param stack_fn: function that stacks residual blocks
:param nodes: width of nodes included in top layer of CNN, int
:return: a Keras model instance
"""
input_shape = (height, width, depth)
img_input = Input(shape=input_shape)
x = ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)
x = Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
x = MaxPooling2D(3, strides=2, name='pool1_pool')(x)
x = stack_fn(x)
# top layer
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(nodes, activation='relu')(x)
# perform regression
x = Dense(1, activation='linear')(x)
model = Model(img_input, x)
return model
def resnet50(height, width, depth, nodes):
def stack_fn(x):
x = stack1(x, 64, 3, stride1=1, name='conv2')
x = stack1(x, 128, 4, name='conv3')
x = stack1(x, 256, 6, name='conv4')
x = stack1(x, 512, 3, name='conv5')
return x
return resnet(height, width, depth, stack_fn, nodes=nodes)
Which can be implemented using some x_train, x_test, y_train, y_test data (where x_train/test is image data and y_train,y_test data are numeric values on the interval [0, 1].
scaler = MinMaxScaler()
images = load_images(df=target, path=PATH_features, resize_shape=(224, 224), quadruple=True)
images = images / 255.0 # scale pixel data to [0, 1]
images = images.astype(np.float32)
imshape = images.shape
target = target[Target]
target = quadruple_target(target, target=Target)
x_train, x_test, y_train, y_test = train_test_split(images, target, test_size=0.3, random_state=101)
y_train = scaler.fit_transform(y_train)
y_test = scaler.transform(y_test)
model = resnet50(imshape[1], imshape[2], imshape[3], nodes=256)
opt = Adam(lr=1e-5, decay=1e-5 / 200)
model.compile(loss=lossFN, optimizer=opt)
history = model.fit(x_train, y_train, validation_data=(x_test, y_test), verbose=1, epochs=200)
pred = model.predict(x_test)

Loading a model in TFLearn - predicting same value each time

I have trained a model on some data using tflearn to do binary classification. The model was trained to a 97% accuracy.
I want to use model.load() in another program to predict the class of some test input data.
However, model.load() only works when I include the argument weights_only=True. When I omit that argument from model.load(), it throws an error:
NotFoundError (see above for traceback): Key is_training not found in checkpoint
When I get the model loaded and run some predictions on my small test set - the classifications seem strange.. The model predicts a perfect 1 in the 1st index every single time. To me this shouldn't be happening if the model was trained to a very high accuracy. Here's what the predictions look like (expected output on the right):
[[ 5.59889193e-22 1.00000000e+00] [0, 1]
[ 4.25160435e-22 1.00000000e+00] [0, 1]
[ 6.65333618e-23 1.00000000e+00] [0, 1]
[ 2.07748895e-21 1.00000000e+00] [0, 1]
[ 1.77639440e-21 1.00000000e+00] [0, 1]
[ 5.77486922e-18 1.00000000e+00] [1, 0]
[ 2.70562403e-19 1.00000000e+00] [1, 0]
[ 2.78288828e-18 1.00000000e+00] [1, 0]
[ 6.10306495e-17 1.00000000e+00] [1, 0]
[ 2.35787162e-19 1.00000000e+00]] [1, 0]
Note: This test data was data used to train the model so should be able to classify correctly with high accuracy.
The code for training the model:
tf.reset_default_graph()
train = pd.read_csv("/Users/darrentaggart/Library/Mobile Documents/com~apple~CloudDocs/Uni Documents/MEE4040 - Project 4/Coding Related Stuff/Neural Networks/modeltraindata_1280.csv")
test = pd.read_csv("/Users/darrentaggart/Library/Mobile Documents/com~apple~CloudDocs/Uni Documents/MEE4040 - Project 4/Coding Related Stuff/Neural Networks/modeltestdata_320.csv")
X = train.iloc[:,1:].values.astype(np.float32)
Y = np.array([np.array([int(i == l) for i in range(2)]) for l in
train.iloc[:,:1].values])
test_x = test.iloc[:,1:].values.astype(np.float32)
test_y = np.array([np.array([int(i == l) for i in range(2)]) for l in
test.iloc[:,:1].values])
X = X.reshape([-1, 16, 16, 1])
test_x = test_x.reshape([-1, 16, 16, 1])
convnet = input_data(shape=[None, 16, 16, 1], name='input')
initialization = tf.contrib.layers.variance_scaling_initializer(factor=1.0, mode='FAN_IN', uniform=False)
convnet = conv_2d(convnet, 32, 2, activation='elu',
weights_init=initialization)
convnet = max_pool_2d(convnet, 2)
convnet = tflearn.layers.normalization.batch_normalization(convnet, beta=0.0, gamma=1.0, epsilon=1e-05,
decay=0.9, stddev=0.002, trainable=True, restore=True, reuse=False, scope=None, name='BatchNormalization')
convnet = conv_2d(convnet, 64, 2, activation='elu',
weights_init=initialization)
convnet = max_pool_2d(convnet, 2)
convnet = tflearn.layers.normalization.batch_normalization(convnet, beta=0.0, gamma=1.0, epsilon=1e-05,
decay=0.9, stddev=0.002, trainable=True, restore=True, reuse=False, scope=None, name='BatchNormalization')
convnet = fully_connected(convnet, 254, activation='elu', weights_init=initialization)
convnet = dropout(convnet, 0.8)
convnet = tflearn.layers.normalization.batch_normalization(convnet, beta=0.0, gamma=1.0, epsilon=1e-05,
decay=0.9, stddev=0.002, trainable=True, restore=True, reuse=False, scope=None, name='BatchNormalization')
convnet = fully_connected(convnet, 2, activation='softmax')
adam = tflearn.optimizers.Adam(learning_rate=0.00065, beta1=0.9, beta2=0.999, epsilon=1e-08)
convnet = regression(convnet, optimizer=adam, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='/Users/darrentaggart/Library/Mobile Documents/com~apple~CloudDocs/Uni Documents/MEE4040 - Project 4/Coding Related Stuff/Neural Networks/latest logs',
tensorboard_verbose=3)
model.fit({'input': X}, {'targets': Y}, n_epoch=100, batch_size=16,
validation_set=({'input': test_x}, {'targets': test_y}), snapshot_step=10, show_metric=True, run_id='1600 - ConvConvFC254 LR0.00065decay BN VSinit 16batchsize 100epochs')
model.save('tflearncnn.model')
Code for loading and generating predictions:
test = pd.read_csv("/Users/darrentaggart/Library/Mobile Documents/com~apple~CloudDocs/Uni Documents/MEE4040 - Project 4/Coding Related Stuff/Neural Networks/modelpredictiondata.csv")
X = test.iloc[:,1:].values.astype(np.float32)
sess=tf.InteractiveSession()
tflearn.is_training(False)
convnet = input_data(shape=[None, 16, 16, 1], name='input')
initialization = tf.contrib.layers.variance_scaling_initializer(factor=1.0, mode='FAN_IN', uniform=False)
convnet = conv_2d(convnet, 32, 2, activation='elu', weights_init=initialization)
convnet = max_pool_2d(convnet, 2)
convnet = tflearn.layers.normalization.batch_normalization(convnet, beta=0.0, gamma=1.0, epsilon=1e-05,
decay=0.9, stddev=0.002, trainable=True, restore=True, reuse=False, scope=None, name='BatchNormalization')
convnet = conv_2d(convnet, 64, 2, activation='elu', weights_init=initialization)
convnet = max_pool_2d(convnet, 2)
convnet = tflearn.layers.normalization.batch_normalization(convnet, beta=0.0, gamma=1.0, epsilon=1e-05,
decay=0.9, stddev=0.002, trainable=True, restore=True, reuse=False, scope=None, name='BatchNormalization')
convnet = fully_connected(convnet, 254, activation='elu', weights_init=initialization)
convnet = tflearn.layers.normalization.batch_normalization(convnet, beta=0.0, gamma=1.0, epsilon=1e-05,
decay=0.9, stddev=0.002, trainable=True, restore=True, reuse=False, scope=None, name='BatchNormalization')
convnet = fully_connected(convnet, 2, activation='softmax')
adam = tflearn.optimizers.Adam(learning_rate=0.00065, beta1=0.9, beta2=0.999, epsilon=1e-08)
convnet = regression(convnet, optimizer=adam, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet)
if os.path.exists('{}.meta'.format('tflearncnn.model')):
model.load('tflearncnn.model', weights_only=False)
print('model loaded!')
for i in enumerate(X):
X = X.reshape([-1, 16, 16, 1])
model_out = model.predict(X)
if np.argmax(model_out) == 1: str_label='Boss'
else: str_label = 'Slot'
print(model_out)
I know it's a long shot but thought someone might be able to shed some light on the matter. Thanks.
It's been a year and a half since this question was asked, but sharing is caring after all. Using tflearn and Alexnet to binary classify an image.
The trick is to normalize after conversion to nparray. Don't forget to change the directory paths.
from __future__ import division, print_function, absolute_import
import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression
from data_utils import *
import os
from PIL import Image
from numpy import array
def res_image(f, image_shape=[224,224], grayscale=False, normalize=True):
img = load_image(f)
width, height = img.size
if width != image_shape[0] or height != image_shape[1]:
img = resize_image(img, image_shape[0], image_shape[1])
if grayscale:
img = convert_color(img, 'L')
elif img.mode == 'L':
img = convert_color(img, 'RGB')
img = pil_to_nparray(img)
if normalize: # << this here is what you need
img /= 255.
img = array(img).reshape(1, image_shape[0], image_shape[1], 3)
return img
# Building the network
network = input_data(shape=[None, 227, 227, 3])
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 2, activation='softmax') # output is the number of outcomes
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
# Training
model = tflearn.DNN(network,
tensorboard_dir=R'C:\Users\b0588718\Source\Repos\AlexNet\AlexNet')
model.load('model.tfl')
f = r'C:\Users\b0588718\Source\Repos\AlexNet\AlexNet\rawdata\jpg\0\P1170047.jpg'
img = res_image(f, [227,227], grayscale=False, normalize=True)
pred = model.predict(img)
print(" %s" % pred[0])
Didn't you try model.load(<path-to-saved-model>).
Ex : model.load("./model.tflearn")
I think this will solve your problem.