Multi-output classification using Tensorflow
I have a multi-output problem (multi-label, multi-classification). In brief, the problem regards instrument recognition in polyphonic music, therefore my model needs to be able to predict the instruments (which can be multiple) in a song.
I need to use a CNN for this. The first block of the network model has been omitted since it is composed only by the feature extractor, with all the convolution, pooling and dropout. I am using the high level API of Tensorflow, Estimators
.
# first part omitted, this is last dropout from a fully connected layer
dropout = tf.layers.dropout(inputs=dense, rate=0.5, training=mode == tf.estimator.ModeKeys.TRAIN)
print('Shape Dropout', dropout.shape)
###########################################################################
# Logits Layer
logits = tf.layers.dense(inputs=dropout, units=labels.shape[1])
print('Shape Logits:', logits.shape)
predictions = tf.round(tf.sigmoid(logits))
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
loss = tf.nn.weighted_cross_entropy_with_logits(targets=tf.cast(labels, tf.float32), logits=logits, pos_weight=3, name=None)
loss = tf.reduce_mean(tf.reduce_sum(loss, axis=1))
accuracy = tf.reduce_mean(tf.cast(tf.equal(predictions, tf.round(tf.cast(labels, tf.float32))), tf.float32))
# calculate f1_score, precision and recall for multilabel problem
f1s = [0, 0, 0]
labels = tf.cast(labels, tf.float64)
predictions = tf.cast(predictions, tf.float64)
for i, axis in enumerate([None, 0]):
TP = tf.count_nonzero(predictions * labels, axis=axis)
FP = tf.count_nonzero(predictions * (labels - 1), axis=axis)
FN = tf.count_nonzero((predictions - 1) * labels, axis=axis)
precision = tf.truediv(TP, (TP + FP))
recall = tf.truediv(TP, (TP + FN))
f1 = 2 * precision * recall / (precision + recall)
f1s[i] = tf.reduce_mean(f1)
weights = tf.reduce_sum(labels, axis=0)
weights /= tf.reduce_sum(weights)
f1s[2] = tf.reduce_sum(tf.cast(f1, tf.float64) * weights)
micro, macro, weighted = f1s
tf.summary.scalar("micro_mLabels", micro)
tf.summary.scalar("macro_mLabels", macro)
tf.summary.scalar("weighted_mLabels", weighted)
tf.summary.scalar("precision_sLabel", tf.metrics.precision(labels=labels, predictions=tf.cast(predictions, tf.int32)))
tf.summary.scalar("recall_sLabel",tf.metrics.recall(labels=labels, predictions=tf.cast(predictions, tf.int32)))
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
logging_hook = tf.train.LoggingTensorHook({"loss": loss, "accuracy": accuracy}, every_n_iter=10)
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op, training_hooks = [logging_hook])
eval_metric_ops = {
"accuracy_sLabel": tf.metrics.accuracy(
labels=labels,
predictions=predictions),
"precision_sLabel": tf.metrics.precision(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
"recall_sLabel": tf.metrics.recall(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
}
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
I recalculate precision and recall internally to check whether was a Tensorflow bug.
Basically, the problem I am having is that the accuracy is really high from the beginning, like in 20 iterations is already at 90% (very weird, should take few epochs), precision and recall differently sometimes are 0 and sometimes not, depending from what hyperparameters I set.
I understand I need to follow a Sigmoid approach for multi-label but I think I am doing things in a wrong way.
What I believe is that the way in which I store the predictions
from the logits
and in how I calculate the loss
is wrong. However, I am not quite sure about the rest of the code, that's why I added the full block.
Really appreciate some help,
Thank you in advance.
python tensorflow
add a comment |
I have a multi-output problem (multi-label, multi-classification). In brief, the problem regards instrument recognition in polyphonic music, therefore my model needs to be able to predict the instruments (which can be multiple) in a song.
I need to use a CNN for this. The first block of the network model has been omitted since it is composed only by the feature extractor, with all the convolution, pooling and dropout. I am using the high level API of Tensorflow, Estimators
.
# first part omitted, this is last dropout from a fully connected layer
dropout = tf.layers.dropout(inputs=dense, rate=0.5, training=mode == tf.estimator.ModeKeys.TRAIN)
print('Shape Dropout', dropout.shape)
###########################################################################
# Logits Layer
logits = tf.layers.dense(inputs=dropout, units=labels.shape[1])
print('Shape Logits:', logits.shape)
predictions = tf.round(tf.sigmoid(logits))
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
loss = tf.nn.weighted_cross_entropy_with_logits(targets=tf.cast(labels, tf.float32), logits=logits, pos_weight=3, name=None)
loss = tf.reduce_mean(tf.reduce_sum(loss, axis=1))
accuracy = tf.reduce_mean(tf.cast(tf.equal(predictions, tf.round(tf.cast(labels, tf.float32))), tf.float32))
# calculate f1_score, precision and recall for multilabel problem
f1s = [0, 0, 0]
labels = tf.cast(labels, tf.float64)
predictions = tf.cast(predictions, tf.float64)
for i, axis in enumerate([None, 0]):
TP = tf.count_nonzero(predictions * labels, axis=axis)
FP = tf.count_nonzero(predictions * (labels - 1), axis=axis)
FN = tf.count_nonzero((predictions - 1) * labels, axis=axis)
precision = tf.truediv(TP, (TP + FP))
recall = tf.truediv(TP, (TP + FN))
f1 = 2 * precision * recall / (precision + recall)
f1s[i] = tf.reduce_mean(f1)
weights = tf.reduce_sum(labels, axis=0)
weights /= tf.reduce_sum(weights)
f1s[2] = tf.reduce_sum(tf.cast(f1, tf.float64) * weights)
micro, macro, weighted = f1s
tf.summary.scalar("micro_mLabels", micro)
tf.summary.scalar("macro_mLabels", macro)
tf.summary.scalar("weighted_mLabels", weighted)
tf.summary.scalar("precision_sLabel", tf.metrics.precision(labels=labels, predictions=tf.cast(predictions, tf.int32)))
tf.summary.scalar("recall_sLabel",tf.metrics.recall(labels=labels, predictions=tf.cast(predictions, tf.int32)))
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
logging_hook = tf.train.LoggingTensorHook({"loss": loss, "accuracy": accuracy}, every_n_iter=10)
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op, training_hooks = [logging_hook])
eval_metric_ops = {
"accuracy_sLabel": tf.metrics.accuracy(
labels=labels,
predictions=predictions),
"precision_sLabel": tf.metrics.precision(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
"recall_sLabel": tf.metrics.recall(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
}
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
I recalculate precision and recall internally to check whether was a Tensorflow bug.
Basically, the problem I am having is that the accuracy is really high from the beginning, like in 20 iterations is already at 90% (very weird, should take few epochs), precision and recall differently sometimes are 0 and sometimes not, depending from what hyperparameters I set.
I understand I need to follow a Sigmoid approach for multi-label but I think I am doing things in a wrong way.
What I believe is that the way in which I store the predictions
from the logits
and in how I calculate the loss
is wrong. However, I am not quite sure about the rest of the code, that's why I added the full block.
Really appreciate some help,
Thank you in advance.
python tensorflow
add a comment |
I have a multi-output problem (multi-label, multi-classification). In brief, the problem regards instrument recognition in polyphonic music, therefore my model needs to be able to predict the instruments (which can be multiple) in a song.
I need to use a CNN for this. The first block of the network model has been omitted since it is composed only by the feature extractor, with all the convolution, pooling and dropout. I am using the high level API of Tensorflow, Estimators
.
# first part omitted, this is last dropout from a fully connected layer
dropout = tf.layers.dropout(inputs=dense, rate=0.5, training=mode == tf.estimator.ModeKeys.TRAIN)
print('Shape Dropout', dropout.shape)
###########################################################################
# Logits Layer
logits = tf.layers.dense(inputs=dropout, units=labels.shape[1])
print('Shape Logits:', logits.shape)
predictions = tf.round(tf.sigmoid(logits))
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
loss = tf.nn.weighted_cross_entropy_with_logits(targets=tf.cast(labels, tf.float32), logits=logits, pos_weight=3, name=None)
loss = tf.reduce_mean(tf.reduce_sum(loss, axis=1))
accuracy = tf.reduce_mean(tf.cast(tf.equal(predictions, tf.round(tf.cast(labels, tf.float32))), tf.float32))
# calculate f1_score, precision and recall for multilabel problem
f1s = [0, 0, 0]
labels = tf.cast(labels, tf.float64)
predictions = tf.cast(predictions, tf.float64)
for i, axis in enumerate([None, 0]):
TP = tf.count_nonzero(predictions * labels, axis=axis)
FP = tf.count_nonzero(predictions * (labels - 1), axis=axis)
FN = tf.count_nonzero((predictions - 1) * labels, axis=axis)
precision = tf.truediv(TP, (TP + FP))
recall = tf.truediv(TP, (TP + FN))
f1 = 2 * precision * recall / (precision + recall)
f1s[i] = tf.reduce_mean(f1)
weights = tf.reduce_sum(labels, axis=0)
weights /= tf.reduce_sum(weights)
f1s[2] = tf.reduce_sum(tf.cast(f1, tf.float64) * weights)
micro, macro, weighted = f1s
tf.summary.scalar("micro_mLabels", micro)
tf.summary.scalar("macro_mLabels", macro)
tf.summary.scalar("weighted_mLabels", weighted)
tf.summary.scalar("precision_sLabel", tf.metrics.precision(labels=labels, predictions=tf.cast(predictions, tf.int32)))
tf.summary.scalar("recall_sLabel",tf.metrics.recall(labels=labels, predictions=tf.cast(predictions, tf.int32)))
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
logging_hook = tf.train.LoggingTensorHook({"loss": loss, "accuracy": accuracy}, every_n_iter=10)
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op, training_hooks = [logging_hook])
eval_metric_ops = {
"accuracy_sLabel": tf.metrics.accuracy(
labels=labels,
predictions=predictions),
"precision_sLabel": tf.metrics.precision(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
"recall_sLabel": tf.metrics.recall(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
}
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
I recalculate precision and recall internally to check whether was a Tensorflow bug.
Basically, the problem I am having is that the accuracy is really high from the beginning, like in 20 iterations is already at 90% (very weird, should take few epochs), precision and recall differently sometimes are 0 and sometimes not, depending from what hyperparameters I set.
I understand I need to follow a Sigmoid approach for multi-label but I think I am doing things in a wrong way.
What I believe is that the way in which I store the predictions
from the logits
and in how I calculate the loss
is wrong. However, I am not quite sure about the rest of the code, that's why I added the full block.
Really appreciate some help,
Thank you in advance.
python tensorflow
I have a multi-output problem (multi-label, multi-classification). In brief, the problem regards instrument recognition in polyphonic music, therefore my model needs to be able to predict the instruments (which can be multiple) in a song.
I need to use a CNN for this. The first block of the network model has been omitted since it is composed only by the feature extractor, with all the convolution, pooling and dropout. I am using the high level API of Tensorflow, Estimators
.
# first part omitted, this is last dropout from a fully connected layer
dropout = tf.layers.dropout(inputs=dense, rate=0.5, training=mode == tf.estimator.ModeKeys.TRAIN)
print('Shape Dropout', dropout.shape)
###########################################################################
# Logits Layer
logits = tf.layers.dense(inputs=dropout, units=labels.shape[1])
print('Shape Logits:', logits.shape)
predictions = tf.round(tf.sigmoid(logits))
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
loss = tf.nn.weighted_cross_entropy_with_logits(targets=tf.cast(labels, tf.float32), logits=logits, pos_weight=3, name=None)
loss = tf.reduce_mean(tf.reduce_sum(loss, axis=1))
accuracy = tf.reduce_mean(tf.cast(tf.equal(predictions, tf.round(tf.cast(labels, tf.float32))), tf.float32))
# calculate f1_score, precision and recall for multilabel problem
f1s = [0, 0, 0]
labels = tf.cast(labels, tf.float64)
predictions = tf.cast(predictions, tf.float64)
for i, axis in enumerate([None, 0]):
TP = tf.count_nonzero(predictions * labels, axis=axis)
FP = tf.count_nonzero(predictions * (labels - 1), axis=axis)
FN = tf.count_nonzero((predictions - 1) * labels, axis=axis)
precision = tf.truediv(TP, (TP + FP))
recall = tf.truediv(TP, (TP + FN))
f1 = 2 * precision * recall / (precision + recall)
f1s[i] = tf.reduce_mean(f1)
weights = tf.reduce_sum(labels, axis=0)
weights /= tf.reduce_sum(weights)
f1s[2] = tf.reduce_sum(tf.cast(f1, tf.float64) * weights)
micro, macro, weighted = f1s
tf.summary.scalar("micro_mLabels", micro)
tf.summary.scalar("macro_mLabels", macro)
tf.summary.scalar("weighted_mLabels", weighted)
tf.summary.scalar("precision_sLabel", tf.metrics.precision(labels=labels, predictions=tf.cast(predictions, tf.int32)))
tf.summary.scalar("recall_sLabel",tf.metrics.recall(labels=labels, predictions=tf.cast(predictions, tf.int32)))
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
logging_hook = tf.train.LoggingTensorHook({"loss": loss, "accuracy": accuracy}, every_n_iter=10)
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op, training_hooks = [logging_hook])
eval_metric_ops = {
"accuracy_sLabel": tf.metrics.accuracy(
labels=labels,
predictions=predictions),
"precision_sLabel": tf.metrics.precision(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
"recall_sLabel": tf.metrics.recall(
labels=labels,
predictions=tf.cast(predictions, tf.int32)),
}
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
I recalculate precision and recall internally to check whether was a Tensorflow bug.
Basically, the problem I am having is that the accuracy is really high from the beginning, like in 20 iterations is already at 90% (very weird, should take few epochs), precision and recall differently sometimes are 0 and sometimes not, depending from what hyperparameters I set.
I understand I need to follow a Sigmoid approach for multi-label but I think I am doing things in a wrong way.
What I believe is that the way in which I store the predictions
from the logits
and in how I calculate the loss
is wrong. However, I am not quite sure about the rest of the code, that's why I added the full block.
Really appreciate some help,
Thank you in advance.
python tensorflow
python tensorflow
asked Nov 13 '18 at 19:17
ldgldg
103216
103216
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53288068%2fmulti-output-classification-using-tensorflow%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53288068%2fmulti-output-classification-using-tensorflow%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown