Talvez eu esteja fazendo previsões erradas?

Aqui está o projeto ... Tenho uma imagem de entrada em escala de cinza que estou tentando segmentar. A segmentação é uma classificação binária simples (pense em primeiro plano versus segundo plano). Portanto, a verdade básica (y) é uma matriz de 0 e 1 - portanto, existem 2 classificações. Ah, e a imagem de entrada é um quadrado, então eu apenas uso uma variável chamadan_input

Minha precisão converge essencialmente para 0,99, mas quando faço uma previsão, recebo todos os zero.EDITAR ->existe um único 1 em cada matriz de saída, ambos no mesmo local ...

Aqui está o código da minha sessão (todo o resto está funcionando) ...

with tf.Session() as sess:
    sess.run(init)
    summary = tf.train.SummaryWriter('/tmp/logdir/', sess.graph_def)
    step = 1
    from tensorflow.contrib.learn.python.learn.datasets.scroll import scroll_data
    data = scroll_data.read_data('/home/kendall/Desktop/')
    # Keep training until reach max iterations
    flag = 0
    # while flag == 0:
    while step * batch_size < training_iters:
        batch_y, batch_x = data.train.next_batch(batch_size)
        # pdb.set_trace()
        # batch_x = batch_x.reshape((batch_size, n_input))
        batch_x = batch_x.reshape((batch_size, n_input, n_input))
        batch_y = batch_y.reshape((batch_size, n_input, n_input))
        batch_y = convert_to_2_channel(batch_y, batch_size)
        # batch_y = batch_y.reshape((batch_size, n_output, n_classes))
        batch_y = batch_y.reshape((batch_size, 200, 200, n_classes))
        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
                                       keep_prob: dropout})
        if step % display_step == 0:
            flag = 1
            # Calculate batch loss and accuracy
            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
                                                              y: batch_y,
                                                              keep_prob: 1.})
            print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
                  "{:.6f}".format(loss) + ", Training Accuracy= " + \
                  "{:.5f}".format(acc)
        step += 1
    print "Optimization Finished!"
    save_path = "model.ckpt"
    saver.save(sess, save_path)

    im = Image.open('/home/kendall/Desktop/HA900_frames/frame0635.tif')
    batch_x = np.array(im)
    pdb.set_trace()
    batch_x = batch_x.reshape((1, n_input, n_input))
    batch_x = batch_x.astype(float)
    # pdb.set_trace()
    prediction = sess.run(pred, feed_dict={x: batch_x, keep_prob: 1.})
    print prediction
    arr1 = np.empty((n_input,n_input))
    arr2 = np.empty((n_input,n_input))
    for i in xrange(n_input):
        for j in xrange(n_input):
            for k in xrange(2):
                if k == 0:
                    arr1[i][j] = prediction[0][i][j][k]
                else:
                    arr2[i][j] = prediction[0][i][j][k]
    # prediction = np.asarray(prediction)
    # prediction = np.reshape(prediction, (200,200))
    # np.savetxt("prediction.csv", prediction, delimiter=",")
    np.savetxt("prediction1.csv", arr1, delimiter=",")
    np.savetxt("prediction2.csv", arr2, delimiter=",")

Como existem duas classificações, essa parte final (com o par de loops) é apenas para particionar a previsão em duas matrizes 2x2.

Salvei as matrizes de previsão em um arquivo CSV e, como eu disse, eram todos zeros.

Também confirmei que todos os dados estão corretos (dimensões e valores).

Por que o treinamento convergiria, mas as previsões são terríveis?

Se você quiser ver todo o código, aqui está ...

import tensorflow as tf
import pdb
import numpy as np
from numpy import genfromtxt
from PIL import Image

# Import MINST data
# from tensorflow.examples.tutorials.mnist import input_data
# mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)


# Parameters
learning_rate = 0.001
training_iters = 20000
batch_size = 128
display_step = 1

# Network Parameters
n_input = 200 # MNIST data input (img shape: 28*28)
n_output = 40000 # MNIST total classes (0-9 digits)
n_classes = 2
#n_input = 200

dropout = 0.75 # Dropout, probability to keep units

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input, n_input])
y = tf.placeholder(tf.float32, [None, n_input, n_input, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)

# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
    # Conv2D wrapper, with bias and relu activation
    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
    x = tf.nn.bias_add(x, b)
    return tf.nn.relu(x)

def maxpool2d(x, k=2):
    # MaxPool2D wrapper
    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
                          padding='SAME')


# Create model
def conv_net(x, weights, biases, dropout):
    # Reshape input picture
    x = tf.reshape(x, shape=[-1, n_input, n_input, 1])

    # Convolution Layer
    conv1 = conv2d(x, weights['wc1'], biases['bc1'])
    # Max Pooling (down-sampling)
    conv1 = maxpool2d(conv1, k=2)
    conv1 = tf.nn.local_response_normalization(conv1)

    # Convolution Layer
    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
    # Max Pooling (down-sampling)
    conv2 = tf.nn.local_response_normalization(conv2)
    conv2 = maxpool2d(conv2, k=2)

    # Convolution Layer
    conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
    # Max Pooling (down-sampling)
    conv3 = tf.nn.local_response_normalization(conv3)
    conv3 = maxpool2d(conv3, k=2)

    # pdb.set_trace()

    # Fully connected layer
    # Reshape conv2 output to fit fully connected layer input
    fc1 = tf.reshape(conv3, [-1, weights['wd1'].get_shape().as_list()[0]])
    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
    fc1 = tf.nn.relu(fc1)
    # Apply Dropout
    fc1 = tf.nn.dropout(fc1, dropout)

    output = []
    for i in xrange(2):
        output.append(tf.nn.softmax(tf.add(tf.matmul(fc1, weights['out']), biases['out'])))

    return output
    # return tf.nn.softmax(tf.add(tf.matmul(fc1, weights['out']), biases['out']))


# Store layers weight & bias
weights = {
    # 5x5 conv, 1 input, 32 outputs
    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
    # 5x5 conv, 32 inputs, 64 outputs
    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
    # 5x5 conv, 32 inputs, 64 outputs
    'wc3': tf.Variable(tf.random_normal([5, 5, 64, 128])),
    # fully connected, 7*7*64 inputs, 1024 outputs
    'wd1': tf.Variable(tf.random_normal([25*25*128, 1024])),
    # 1024 inputs, 10 outputs (class prediction)
    'out': tf.Variable(tf.random_normal([1024, n_output]))
}

biases = {
    'bc1': tf.Variable(tf.random_normal([32])),
    'bc2': tf.Variable(tf.random_normal([64])),
    'bc3': tf.Variable(tf.random_normal([128])),
    'bd1': tf.Variable(tf.random_normal([1024])),
    'out': tf.Variable(tf.random_normal([n_output]))
}

# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# pdb.set_trace()
pred = tf.pack(tf.transpose(pred,[1,2,0]))
pred = tf.reshape(pred, [-1,n_input,n_input,n_classes])
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.initialize_all_variables()
saver = tf.train.Saver()

def convert_to_2_channel(x, batch_size):
    #assume input has dimension (batch_size,x,y)
    #output will have dimension (batch_size,x,y,2)
    output = np.empty((batch_size, 200, 200, 2))

    temp_arr1 = np.empty((batch_size, 200, 200))
    temp_arr2 = np.empty((batch_size, 200, 200))

    for i in xrange(batch_size):
        for j in xrange(200):
            for k in xrange(200):
                if x[i][j][k] == 1:
                    temp_arr1[i][j][k] = 1
                    temp_arr2[i][j][k] = 0
                else:
                    temp_arr1[i][j][k] = 0
                    temp_arr2[i][j][k] = 1

    for i in xrange(batch_size):
        for j in xrange(200):
            for k in xrange(200):
                for l in xrange(2):
                    if l == 0:
                        output[i][j][k][l] = temp_arr1[i][j][k]
                    else:
                        output[i][j][k][l] = temp_arr2[i][j][k]

    return output

# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    summary = tf.train.SummaryWriter('/tmp/logdir/', sess.graph_def)
    step = 1
    from tensorflow.contrib.learn.python.learn.datasets.scroll import scroll_data
    data = scroll_data.read_data('/home/kendall/Desktop/')
    # Keep training until reach max iterations
    flag = 0
    # while flag == 0:
    while step * batch_size < training_iters:
        batch_y, batch_x = data.train.next_batch(batch_size)
        # pdb.set_trace()
        # batch_x = batch_x.reshape((batch_size, n_input))
        batch_x = batch_x.reshape((batch_size, n_input, n_input))
        batch_y = batch_y.reshape((batch_size, n_input, n_input))
        batch_y = convert_to_2_channel(batch_y, batch_size)
        # batch_y = batch_y.reshape((batch_size, n_output, n_classes))
        batch_y = batch_y.reshape((batch_size, 200, 200, n_classes))
        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
                                       keep_prob: dropout})
        if step % display_step == 0:
            flag = 1
            # Calculate batch loss and accuracy
            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
                                                              y: batch_y,
                                                              keep_prob: 1.})
            print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
                  "{:.6f}".format(loss) + ", Training Accuracy= " + \
                  "{:.5f}".format(acc)
        step += 1
    print "Optimization Finished!"
    save_path = "model.ckpt"
    saver.save(sess, save_path)

    im = Image.open('/home/kendall/Desktop/HA900_frames/frame0635.tif')
    batch_x = np.array(im)
    pdb.set_trace()
    batch_x = batch_x.reshape((1, n_input, n_input))
    batch_x = batch_x.astype(float)
    # pdb.set_trace()
    prediction = sess.run(pred, feed_dict={x: batch_x, keep_prob: 1.})
    print prediction
    arr1 = np.empty((n_input,n_input))
    arr2 = np.empty((n_input,n_input))
    for i in xrange(n_input):
        for j in xrange(n_input):
            for k in xrange(2):
                if k == 0:
                    arr1[i][j] = prediction[0][i][j][k]
                else:
                    arr2[i][j] = prediction[0][i][j][k]
    # prediction = np.asarray(prediction)
    # prediction = np.reshape(prediction, (200,200))
    # np.savetxt("prediction.csv", prediction, delimiter=",")
    np.savetxt("prediction1.csv", arr1, delimiter=",")
    np.savetxt("prediction2.csv", arr2, delimiter=",")

    # Calculate accuracy for 256 mnist test images
    print "Testing Accuracy:", \
        sess.run(accuracy, feed_dict={x: data.test.images[:256],
                                      y: data.test.labels[:256],
                                      keep_prob: 1.})