Why does my Keras model learn to recognize the background?Does the time to train a model using keras increase linear with epoches?Keras stateful LSTM returns NaN for validation lossResources to learn Tensorflow and KerasSame input size but cannot fit the model in kerasMy Keras CNN doesn't learnWhy this model does not converge in keras?Why does Keras' Model() have an inputs parameter?Why is my Keras model not learning image segmentation?Keras save model FailedPreconditionErrorkeras model only predicts one class for all the test images
Is it possible to determine the symmetric encryption method used by output size?
How to type a section sign (§) into the Minecraft client
How come there are so many candidates for the 2020 Democratic party presidential nomination?
What language was spoken in East Asia before Proto-Turkic?
Pulling the rope with one hand is as heavy as with two hands?
How to stop co-workers from teasing me because I know Russian?
Why is it that the natural deduction method can't test for invalidity?
Why do games have consumables?
Using a Lyapunov function to classify stability and sketching a phase portrait
Is there any limitation with Arduino Nano serial communication distance?
Why does nature favour the Laplacian?
Does Gita support doctrine of eternal cycle of birth and death for evil people?
A Strange Latex Symbol
How to solve constants out of the internal energy equation?
Will a top journal at least read my introduction?
Don’t seats that recline flat defeat the purpose of having seatbelts?
What are the potential pitfalls when using metals as a currency?
Realistic Necromancy?
Unexpected email from Yorkshire Bank
How to pronounce 'C++' in Spanish
What is the relationship between spectral sequences and obstruction theory?
Phrase for the opposite of "foolproof"
How can I practically buy stocks?
How can Republicans who favour free markets, consistently express anger when they don't like the outcome of that choice?
Why does my Keras model learn to recognize the background?
Does the time to train a model using keras increase linear with epoches?Keras stateful LSTM returns NaN for validation lossResources to learn Tensorflow and KerasSame input size but cannot fit the model in kerasMy Keras CNN doesn't learnWhy this model does not converge in keras?Why does Keras' Model() have an inputs parameter?Why is my Keras model not learning image segmentation?Keras save model FailedPreconditionErrorkeras model only predicts one class for all the test images
$begingroup$
I'm trying to train this Keras implementation of Deeplabv3+ on Pascal VOC2012, using the pretrained model (which was also trained on that dataset).
I got weird results with the accuracy quickly converging to 1.0:
5/5 [==============================] - 182s 36s/step - loss: 26864.4418 - acc: 0.7669 - val_loss: 19385.8555 - val_acc: 0.4818
Epoch 2/3
5/5 [==============================] - 77s 15s/step - loss: 42117.3555 - acc: 0.9815 - val_loss: 69088.5469 - val_acc: 0.9948
Epoch 3/3
5/5 [==============================] - 78s 16s/step - loss: 45300.6992 - acc: 1.0000 - val_loss: 44569.9414 - val_acc: 1.0000
Testing the model also gives 100% accuracy.
I decided to plot predictions on the same set of random images before and after training, and found that the model is encouraged to say everything is just background (that's the 1st class in Pascal VOC2012).
I'm quite new to deep learning and would need help to figure out where this could come from.
I thought that perhaps it could be my loss function, which I defined as:
def image_categorical_cross_entropy(y_true, y_pred):
"""
:param y_true: tensor of shape (batch_size, height, width) representing the ground truth.
:param y_pred: tensor of shape (batch_size, height, width) representing the prediction.
:return: The mean cross-entropy on softmaxed tensors.
"""
return tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y_pred, labels=y_true))
I am a bit uncertain on whether my tensors have the right shape. I'm using TF's dataset API to load .tfrecord files, and my annotation tensor is of shape (batch_size, height, width). Would (batch_size, height, width, 21) be what's needed? Other errors from inside the model arise when I try to separate the annotation image into a tensor containing 21 images (one for each class):
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,512,512,21] vs. [12,512,512]
[[Node: metrics/acc/Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](metrics/acc/ArgMax, metrics/acc/ArgMax_1)]]
[[Node: training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1/_13277 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_62151_training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:1"]()]]
Thank you for your help!
python deep-learning keras tensorflow
asked Oct 3 '18 at 15:06
MattMatt
745
$endgroup$
|
show 1 more comment
$begingroup$
I'm trying to train this Keras implementation of Deeplabv3+ on Pascal VOC2012, using the pretrained model (which was also trained on that dataset).
I got weird results with the accuracy quickly converging to 1.0:
5/5 [==============================] - 182s 36s/step - loss: 26864.4418 - acc: 0.7669 - val_loss: 19385.8555 - val_acc: 0.4818
Epoch 2/3
5/5 [==============================] - 77s 15s/step - loss: 42117.3555 - acc: 0.9815 - val_loss: 69088.5469 - val_acc: 0.9948
Epoch 3/3
5/5 [==============================] - 78s 16s/step - loss: 45300.6992 - acc: 1.0000 - val_loss: 44569.9414 - val_acc: 1.0000
Testing the model also gives 100% accuracy.
I decided to plot predictions on the same set of random images before and after training, and found that the model is encouraged to say everything is just background (that's the 1st class in Pascal VOC2012).
I'm quite new to deep learning and would need help to figure out where this could come from.
I thought that perhaps it could be my loss function, which I defined as:
def image_categorical_cross_entropy(y_true, y_pred):
"""
:param y_true: tensor of shape (batch_size, height, width) representing the ground truth.
:param y_pred: tensor of shape (batch_size, height, width) representing the prediction.
:return: The mean cross-entropy on softmaxed tensors.
"""
return tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y_pred, labels=y_true))
I am a bit uncertain on whether my tensors have the right shape. I'm using TF's dataset API to load .tfrecord files, and my annotation tensor is of shape (batch_size, height, width). Would (batch_size, height, width, 21) be what's needed? Other errors from inside the model arise when I try to separate the annotation image into a tensor containing 21 images (one for each class):
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,512,512,21] vs. [12,512,512]
[[Node: metrics/acc/Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](metrics/acc/ArgMax, metrics/acc/ArgMax_1)]]
[[Node: training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1/_13277 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_62151_training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:1"]()]]
Thank you for your help!
python deep-learning keras tensorflow
asked Oct 3 '18 at 15:06
MattMatt
745
$endgroup$
5
$begingroup$
Quite a few items to consider here, I almost don't know where to start (1) are you using a sample size of 5 for training??? (2) What, if any, pre-processing are you doing to your images? I have a feeling that the answer lies within this and (3) you'd have to provide a lot more info on your model. How many labeled samples do you have? How many possible categories? Do you have a balanced training set? (4) your accuracy of 1.0 basically means nothing because your loss is super-high and increasing. Your loss should decrease as your accuracy improves.
$endgroup$
– I_Play_With_Data
Oct 3 '18 at 15:54
$begingroup$
(1) I'm using batches of size 12 but this is kind of irrelevant I think. I only showed 3 small epochs of only 5 steps here because that's just how quickly it converges. (2) My preprocessing consists of some augmentation and rescaling (possibly cropping) to 512x512 for every image and its associated annotation. (3) there are about 11,500 labeled images in Pascal VOC 2012. Granted most papers reach 85%+ mIOU on this dataset, I would assume it's balanced. There's 20 different categories in this dataset plus one for the background or « ambiguous », for a total of 21.
$endgroup$
– Matt
Oct 3 '18 at 16:19
$begingroup$
I'm curios. Did you find the reason for your model's results?
$endgroup$
– Mark.F
Dec 13 '18 at 10:49
3
$begingroup$
If you shared your code, it would be possible to find the mistake.
$endgroup$
– Dmytro Prylipko
Jan 11 at 15:03
1
$begingroup$
The fact that a pre-trained model finds a way to get 100% accuracy within 3 epochs, using the same data as was originally used, makes me think the bug is that your training labels are wrong, perhaps all set to the label that corresponds to background. In any case, have a look at this issue thread, where people discuss their problems and solutions for fine-tuning the model. The model isn't necessarily broken, and the batchnorm bug in Tensorflow can be addressed.
$endgroup$
– n1k31t4
Mar 2 at 13:28
|
show 1 more comment
$begingroup$
I'm trying to train this Keras implementation of Deeplabv3+ on Pascal VOC2012, using the pretrained model (which was also trained on that dataset).
I got weird results with the accuracy quickly converging to 1.0:
5/5 [==============================] - 182s 36s/step - loss: 26864.4418 - acc: 0.7669 - val_loss: 19385.8555 - val_acc: 0.4818
Epoch 2/3
5/5 [==============================] - 77s 15s/step - loss: 42117.3555 - acc: 0.9815 - val_loss: 69088.5469 - val_acc: 0.9948
Epoch 3/3
5/5 [==============================] - 78s 16s/step - loss: 45300.6992 - acc: 1.0000 - val_loss: 44569.9414 - val_acc: 1.0000
Testing the model also gives 100% accuracy.
I decided to plot predictions on the same set of random images before and after training, and found that the model is encouraged to say everything is just background (that's the 1st class in Pascal VOC2012).
I'm quite new to deep learning and would need help to figure out where this could come from.
I thought that perhaps it could be my loss function, which I defined as:
def image_categorical_cross_entropy(y_true, y_pred):
"""
:param y_true: tensor of shape (batch_size, height, width) representing the ground truth.
:param y_pred: tensor of shape (batch_size, height, width) representing the prediction.
:return: The mean cross-entropy on softmaxed tensors.
"""
return tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y_pred, labels=y_true))
I am a bit uncertain on whether my tensors have the right shape. I'm using TF's dataset API to load .tfrecord files, and my annotation tensor is of shape (batch_size, height, width). Would (batch_size, height, width, 21) be what's needed? Other errors from inside the model arise when I try to separate the annotation image into a tensor containing 21 images (one for each class):
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,512,512,21] vs. [12,512,512]
[[Node: metrics/acc/Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](metrics/acc/ArgMax, metrics/acc/ArgMax_1)]]
[[Node: training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1/_13277 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_62151_training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:1"]()]]
Thank you for your help!
python deep-learning keras tensorflow
asked Oct 3 '18 at 15:06
MattMatt
745
$endgroup$
I'm trying to train this Keras implementation of Deeplabv3+ on Pascal VOC2012, using the pretrained model (which was also trained on that dataset).
I got weird results with the accuracy quickly converging to 1.0:
5/5 [==============================] - 182s 36s/step - loss: 26864.4418 - acc: 0.7669 - val_loss: 19385.8555 - val_acc: 0.4818
Epoch 2/3
5/5 [==============================] - 77s 15s/step - loss: 42117.3555 - acc: 0.9815 - val_loss: 69088.5469 - val_acc: 0.9948
Epoch 3/3
5/5 [==============================] - 78s 16s/step - loss: 45300.6992 - acc: 1.0000 - val_loss: 44569.9414 - val_acc: 1.0000
Testing the model also gives 100% accuracy.
I decided to plot predictions on the same set of random images before and after training, and found that the model is encouraged to say everything is just background (that's the 1st class in Pascal VOC2012).
I'm quite new to deep learning and would need help to figure out where this could come from.
I thought that perhaps it could be my loss function, which I defined as:
def image_categorical_cross_entropy(y_true, y_pred):
"""
:param y_true: tensor of shape (batch_size, height, width) representing the ground truth.
:param y_pred: tensor of shape (batch_size, height, width) representing the prediction.
:return: The mean cross-entropy on softmaxed tensors.
"""
return tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y_pred, labels=y_true))
I am a bit uncertain on whether my tensors have the right shape. I'm using TF's dataset API to load .tfrecord files, and my annotation tensor is of shape (batch_size, height, width). Would (batch_size, height, width, 21) be what's needed? Other errors from inside the model arise when I try to separate the annotation image into a tensor containing 21 images (one for each class):
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [12,512,512,21] vs. [12,512,512]
[[Node: metrics/acc/Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/device:GPU:0"](metrics/acc/ArgMax, metrics/acc/ArgMax_1)]]
[[Node: training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1/_13277 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_62151_training/Adam/gradients/bilinear_upsampling_2_1/concat_grad/Slice_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:1"]()]]
Thank you for your help!
python deep-learning keras tensorflow
python deep-learning keras tensorflow
asked Oct 3 '18 at 15:06
MattMatt
745
asked Oct 3 '18 at 15:06
MattMatt
745
edited Oct 5 '18 at 17:31
Matt
asked Oct 3 '18 at 15:06
MattMatt
745
asked Oct 3 '18 at 15:06
MattMatt
745
asked Oct 3 '18 at 15:06
MattMatt
745
745
5
$begingroup$
Quite a few items to consider here, I almost don't know where to start (1) are you using a sample size of 5 for training??? (2) What, if any, pre-processing are you doing to your images? I have a feeling that the answer lies within this and (3) you'd have to provide a lot more info on your model. How many labeled samples do you have? How many possible categories? Do you have a balanced training set? (4) your accuracy of 1.0 basically means nothing because your loss is super-high and increasing. Your loss should decrease as your accuracy improves.
$endgroup$
– I_Play_With_Data
Oct 3 '18 at 15:54
$begingroup$
(1) I'm using batches of size 12 but this is kind of irrelevant I think. I only showed 3 small epochs of only 5 steps here because that's just how quickly it converges. (2) My preprocessing consists of some augmentation and rescaling (possibly cropping) to 512x512 for every image and its associated annotation. (3) there are about 11,500 labeled images in Pascal VOC 2012. Granted most papers reach 85%+ mIOU on this dataset, I would assume it's balanced. There's 20 different categories in this dataset plus one for the background or « ambiguous », for a total of 21.
$endgroup$
– Matt
Oct 3 '18 at 16:19
$begingroup$
I'm curios. Did you find the reason for your model's results?
$endgroup$
– Mark.F
Dec 13 '18 at 10:49
3
$begingroup$
If you shared your code, it would be possible to find the mistake.
$endgroup$
– Dmytro Prylipko
Jan 11 at 15:03
1
$begingroup$
The fact that a pre-trained model finds a way to get 100% accuracy within 3 epochs, using the same data as was originally used, makes me think the bug is that your training labels are wrong, perhaps all set to the label that corresponds to background. In any case, have a look at this issue thread, where people discuss their problems and solutions for fine-tuning the model. The model isn't necessarily broken, and the batchnorm bug in Tensorflow can be addressed.
$endgroup$
– n1k31t4
Mar 2 at 13:28
|
show 1 more comment
5
$begingroup$
Quite a few items to consider here, I almost don't know where to start (1) are you using a sample size of 5 for training??? (2) What, if any, pre-processing are you doing to your images? I have a feeling that the answer lies within this and (3) you'd have to provide a lot more info on your model. How many labeled samples do you have? How many possible categories? Do you have a balanced training set? (4) your accuracy of 1.0 basically means nothing because your loss is super-high and increasing. Your loss should decrease as your accuracy improves.
$endgroup$
– I_Play_With_Data
Oct 3 '18 at 15:54
$begingroup$
(1) I'm using batches of size 12 but this is kind of irrelevant I think. I only showed 3 small epochs of only 5 steps here because that's just how quickly it converges. (2) My preprocessing consists of some augmentation and rescaling (possibly cropping) to 512x512 for every image and its associated annotation. (3) there are about 11,500 labeled images in Pascal VOC 2012. Granted most papers reach 85%+ mIOU on this dataset, I would assume it's balanced. There's 20 different categories in this dataset plus one for the background or « ambiguous », for a total of 21.
$endgroup$
– Matt
Oct 3 '18 at 16:19
$begingroup$
I'm curios. Did you find the reason for your model's results?
$endgroup$
– Mark.F
Dec 13 '18 at 10:49
3
$begingroup$
If you shared your code, it would be possible to find the mistake.
$endgroup$
– Dmytro Prylipko
Jan 11 at 15:03
1
$begingroup$
The fact that a pre-trained model finds a way to get 100% accuracy within 3 epochs, using the same data as was originally used, makes me think the bug is that your training labels are wrong, perhaps all set to the label that corresponds to background. In any case, have a look at this issue thread, where people discuss their problems and solutions for fine-tuning the model. The model isn't necessarily broken, and the batchnorm bug in Tensorflow can be addressed.
$endgroup$
– n1k31t4
Mar 2 at 13:28
5
5
$begingroup$
Quite a few items to consider here, I almost don't know where to start (1) are you using a sample size of 5 for training??? (2) What, if any, pre-processing are you doing to your images? I have a feeling that the answer lies within this and (3) you'd have to provide a lot more info on your model. How many labeled samples do you have? How many possible categories? Do you have a balanced training set? (4) your accuracy of 1.0 basically means nothing because your loss is super-high and increasing. Your loss should decrease as your accuracy improves.
$endgroup$
– I_Play_With_Data
Oct 3 '18 at 15:54
$begingroup$
Quite a few items to consider here, I almost don't know where to start (1) are you using a sample size of 5 for training??? (2) What, if any, pre-processing are you doing to your images? I have a feeling that the answer lies within this and (3) you'd have to provide a lot more info on your model. How many labeled samples do you have? How many possible categories? Do you have a balanced training set? (4) your accuracy of 1.0 basically means nothing because your loss is super-high and increasing. Your loss should decrease as your accuracy improves.
$endgroup$
– I_Play_With_Data
Oct 3 '18 at 15:54
$begingroup$
(1) I'm using batches of size 12 but this is kind of irrelevant I think. I only showed 3 small epochs of only 5 steps here because that's just how quickly it converges. (2) My preprocessing consists of some augmentation and rescaling (possibly cropping) to 512x512 for every image and its associated annotation. (3) there are about 11,500 labeled images in Pascal VOC 2012. Granted most papers reach 85%+ mIOU on this dataset, I would assume it's balanced. There's 20 different categories in this dataset plus one for the background or « ambiguous », for a total of 21.
$endgroup$
– Matt
Oct 3 '18 at 16:19
$begingroup$
(1) I'm using batches of size 12 but this is kind of irrelevant I think. I only showed 3 small epochs of only 5 steps here because that's just how quickly it converges. (2) My preprocessing consists of some augmentation and rescaling (possibly cropping) to 512x512 for every image and its associated annotation. (3) there are about 11,500 labeled images in Pascal VOC 2012. Granted most papers reach 85%+ mIOU on this dataset, I would assume it's balanced. There's 20 different categories in this dataset plus one for the background or « ambiguous », for a total of 21.
$endgroup$
– Matt
Oct 3 '18 at 16:19
$begingroup$
I'm curios. Did you find the reason for your model's results?
$endgroup$
– Mark.F
Dec 13 '18 at 10:49
$begingroup$
I'm curios. Did you find the reason for your model's results?
$endgroup$
– Mark.F
Dec 13 '18 at 10:49
3
3
$begingroup$
If you shared your code, it would be possible to find the mistake.
$endgroup$
– Dmytro Prylipko
Jan 11 at 15:03
$begingroup$
If you shared your code, it would be possible to find the mistake.
$endgroup$
– Dmytro Prylipko
Jan 11 at 15:03
1
1
$begingroup$
The fact that a pre-trained model finds a way to get 100% accuracy within 3 epochs, using the same data as was originally used, makes me think the bug is that your training labels are wrong, perhaps all set to the label that corresponds to background. In any case, have a look at this issue thread, where people discuss their problems and solutions for fine-tuning the model. The model isn't necessarily broken, and the batchnorm bug in Tensorflow can be addressed.
$endgroup$
– n1k31t4
Mar 2 at 13:28
$begingroup$
The fact that a pre-trained model finds a way to get 100% accuracy within 3 epochs, using the same data as was originally used, makes me think the bug is that your training labels are wrong, perhaps all set to the label that corresponds to background. In any case, have a look at this issue thread, where people discuss their problems and solutions for fine-tuning the model. The model isn't necessarily broken, and the batchnorm bug in Tensorflow can be addressed.
$endgroup$
– n1k31t4
Mar 2 at 13:28
|
show 1 more comment
1 Answer
1
active
oldest
votes
$begingroup$
Your model is overfitting. Each epoch only has 5 images. The model is "memorizing" the answer for each image.
In order to minimize the chance of overfitting, increase the number of images. There should be several thousand example images for each category of object.
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
$endgroup$
add a comment |
Your Answer
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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%2fdatascience.stackexchange.com%2fquestions%2f39117%2fwhy-does-my-keras-model-learn-to-recognize-the-background%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
Your model is overfitting. Each epoch only has 5 images. The model is "memorizing" the answer for each image.
In order to minimize the chance of overfitting, increase the number of images. There should be several thousand example images for each category of object.
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
$endgroup$
add a comment |
$begingroup$
Your model is overfitting. Each epoch only has 5 images. The model is "memorizing" the answer for each image.
In order to minimize the chance of overfitting, increase the number of images. There should be several thousand example images for each category of object.
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
$endgroup$
add a comment |
$begingroup$
Your model is overfitting. Each epoch only has 5 images. The model is "memorizing" the answer for each image.
In order to minimize the chance of overfitting, increase the number of images. There should be several thousand example images for each category of object.
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
$endgroup$
Your model is overfitting. Each epoch only has 5 images. The model is "memorizing" the answer for each image.
In order to minimize the chance of overfitting, increase the number of images. There should be several thousand example images for each category of object.
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
answered Apr 8 at 0:18
Brian SpieringBrian Spiering
4,3531129
4,3531129
add a comment |
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- 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.
Use MathJax to format equations. MathJax reference.
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%2fdatascience.stackexchange.com%2fquestions%2f39117%2fwhy-does-my-keras-model-learn-to-recognize-the-background%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
5
$begingroup$
Quite a few items to consider here, I almost don't know where to start (1) are you using a sample size of 5 for training??? (2) What, if any, pre-processing are you doing to your images? I have a feeling that the answer lies within this and (3) you'd have to provide a lot more info on your model. How many labeled samples do you have? How many possible categories? Do you have a balanced training set? (4) your accuracy of 1.0 basically means nothing because your loss is super-high and increasing. Your loss should decrease as your accuracy improves.
$endgroup$
– I_Play_With_Data
Oct 3 '18 at 15:54
$begingroup$
(1) I'm using batches of size 12 but this is kind of irrelevant I think. I only showed 3 small epochs of only 5 steps here because that's just how quickly it converges. (2) My preprocessing consists of some augmentation and rescaling (possibly cropping) to 512x512 for every image and its associated annotation. (3) there are about 11,500 labeled images in Pascal VOC 2012. Granted most papers reach 85%+ mIOU on this dataset, I would assume it's balanced. There's 20 different categories in this dataset plus one for the background or « ambiguous », for a total of 21.
$endgroup$
– Matt
Oct 3 '18 at 16:19
$begingroup$
I'm curios. Did you find the reason for your model's results?
$endgroup$
– Mark.F
Dec 13 '18 at 10:49
3
$begingroup$
If you shared your code, it would be possible to find the mistake.
$endgroup$
– Dmytro Prylipko
Jan 11 at 15:03
1
$begingroup$
The fact that a pre-trained model finds a way to get 100% accuracy within 3 epochs, using the same data as was originally used, makes me think the bug is that your training labels are wrong, perhaps all set to the label that corresponds to background. In any case, have a look at this issue thread, where people discuss their problems and solutions for fine-tuning the model. The model isn't necessarily broken, and the batchnorm bug in Tensorflow can be addressed.
$endgroup$
– n1k31t4
Mar 2 at 13:28