machine learning - Model in Tensorflow is not Working need review of the code not sure whats going Wrong -
i modifying deep mnist code own data. modified model bit facing basic issues pass data model 1 one , runs reall fast when pass model examples @ ones gets slow , getting 0% accuracy. kindly review code doing horribly wrong not know , steps should follow make correct.
here model
def deepnn(x): """deepnn builds graph deep net classifying digits. args: x: input tensor dimensions (n_examples, 784), 784 number of pixels in standard mnist image. returns: tuple (y, keep_prob). y tensor of shape (n_examples, 10), values equal logits of classifying digit 1 of 10 classes (the digits 0-9). keep_prob scalar placeholder probability of dropout. """ x_image = tf.reshape(x, [-1, 28, 28, 1]) w_conv1 = weight_variable([5, 5, 1, 200]) b_conv1 = bias_variable([200]) h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) w_conv2 = weight_variable([5, 5, 200, 100]) b_conv2 = bias_variable([100]) h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2) w_fc1 = weight_variable([7 * 7 * 100, 1024]) b_fc1 = bias_variable([1024]) h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*100]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1) keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) w_fc2 = weight_variable([1024, 19]) b_fc2 = bias_variable([19]) y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2 return y_conv, keep_prob here fucntion model calls.
def conv2d(x, w): """conv2d returns 2d convolution layer full stride.""" return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='same') def max_pool_2x2(x): """max_pool_2x2 downsamples feature map 2x.""" return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='same') def weight_variable(shape): """weight_variable generates weight variable of given shape.""" initial = tf.truncated_normal(shape, stddev=0.1) return tf.variable(initial) def bias_variable(shape): """bias_variable generates bias variable of given shape.""" initial = tf.constant(0.1, shape=shape) return tf.variable(initial) and main
def main(_): x = tf.placeholder(tf.float32, [none, 784]) y_ = tf.placeholder(tf.float32, [none, 19]) y_conv, keep_prob = deepnn(x) cross_entropy tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)) train_step = tf.train.adamoptimizer(1e-4).minimize(cross_entropy) correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) tf.session() sess: sess.run(tf.global_variables_initializer()) in range(34670): #batch = mnist.train.next_batch(50) if % 1000 == 0: train_accuracy = accuracy.eval(feed_dict={x: np.reshape(input_to_nn(i),(-1,784)), y_:np.reshape(output_of_nn(i),(-1,19)), keep_prob: 1.0}) print('step %d, training accuracy %g' % (i, train_accuracy)) train_step.run(feed_dict={x: np.reshape(input_to_nn(i),(-1,784)), y_:np.reshape(output_of_nn(i),(-1,19)), keep_prob: 0.5}) print('test accuracy %g' % accuracy.eval(feed_dict={x:input_nn, y_:output_nn, keep_prob: 1.0}))
i think problem in these lines:
w_fc2 = weight_variable([1024, 19]) b_fc2 = bias_variable([19]) your model trains predict 19 classes. there 10 digit, if don't have images 19 classes, better revert values original 10.
Comments
Post a Comment