I am trying to figure out what loss functions are used in ssdlite_mobilenet_v2_coco but I can't seem to find where it is specified in the repo or online. This is my Tensorboard for my loss while training but it doesn't specify what the loss metric is.
Link to repo: https://github.com/tensorflow/models/tree/master/research/object_detection
I am following this tutorial:
https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10#8-use-your-newly-trained-object-detection-classifier
I've tried looking through the config file and some parts of the code but didn't see what type of metric it uses.
Is there a location where I can find the loss metric used for each type of model architecture on the repo? Thanks!
You can see the loss functions used in the config file. The loss is comprised of two losses: weighted_sigmoid for classification, weighted_smooth_l1 for localization, each with weight of 1. To see the code of these losses you can check the loss functions here. Note the total loss has another component for regularization.
Related
I'm trying to obtain the loss of each image compared to the autoencoder prediction. I am able to obtain the mean loss per epoch, but I would like to see how it holds for different types of images (slightly different from the trained set) to see how it performs.
Found it here: https://keras.io/api/losses/ under "Standalone usage of loss".
I am using Keras with a tensorflow backend to train some CNNs for semantic segmentation of biomedical images. I am trying to weight every pixel in my input images during training and believe I am doing so with the data generator I am passing to model.fit.
However, I am a little confused about the meaning of 'sample_weights' vs. 'sample_weight' in the documentation for model.fit.
'sample_weights' is the third optional output from your dataset or image generator - i.e. the output of the generator can either be the tuple (inputs, targets) or the tuple (inputs, targets, sample_weights). I believe this lets me create a mask that weights my samples pixel-by-pixels, but this isn't super clear from the documentation.
'sample_weight' is a separate field that seems to be pretty clearly defined as a weight you can give to every sample. If I understand, this would allow me to give more or less weight to particular images in my training set.
Do I have this right? Thanks.
I am pretty new to tensorflow and I am struggling to get tensorboard to display some of my custom metrics. The model I am working with is a tf.estimator.Estimator, with an associated EstimatorSpec. The first new metric I am trying to log is from my loss function, which is composed of two components: a loss for an age prediction (tf.float32) and a loss for a class prediction (one-hot/multiclass), which I add together to determine a total loss (my model is predicting both a class and an age). The total loss is output just fine during training and shows up on tensorboard, but I would like to track the individual age and the class prediction loss components as well.
I think a solution that is supposed to work is to add a eval_metric_ops argument to the EstimatorSpec as described here (Custom eval_metric_ops in Estimator in Tensorflow). I have not been able to make this approach work, however. I defined a custom metric function that looks like this:
def age_loss_function(labels, ages_pred, ages_true):
per_sample_age_loss = get_age_loss_per_sample(ages_pred, ages_true) ### works fine
#### The error happens on this line:
mean_abs_age_diff, age_loss_update_fn = tf.metrics.Mean(per_sample_age_loss)
######
return mean_abs_age_diff, age_loss_update_fn
eval_metric_ops = {"age_loss": age_loss_function} #### Want to use this in EstimatorSpec
The instructions seem to say that I need both the error metric and the update function which should both be returned from the tf.metrics command as in examples like the one I linked. But this command fails for me with the error message:
tensorflow.python.framework.errors_impl.OperatorNotAllowedInGraphError: using a `tf.Tensor` as a Python `bool` is not allowed in Graph execution. Use Eager execution or decorate this function with #tf.function.
I am probably just misusing the APIs. If someone can guide me on the proper usage I would really appreciate it. Thanks!
It looks like the problem was from a version change. I had updated to tensorflow 2.0 while the instructions I was following were from 1.X. Using tf.compat.v1.metrics.mean() instead gets past this problem.
I am running the tensorflow object detection API and using the SSD_mobilenet model.I have the model.cpkt as well as the graph.pbtxt in my training dir. But in my training dir I found that my events files are empty. It seems that no data was written to my events. Could anyone help me,please!!!
Tensorflow event files will be generated based on the summaries what we have added in code.
For example, suppose you are training a convolutional neural network for recognizing MNIST digits. You'd like to record how the learning rate varies over time, and how the objective function is changing. Collect these by attaching tf.summary.scalar ops to the nodes that output the learning rate and loss respectively. Then, give each scalar_summary a meaningful tag, like 'learning rate' or 'loss function'.
For example:
Add a scalar summary for the snapshot loss.
tf.summary.scalar('loss', loss)
Please refer the below link:
https://www.tensorflow.org/guide/summaries_and_tensorboard
Output of the following tensorflow function should give average log perplexity. I went through the source code. But I don't understand how they calculate that loss.
tf.contrib.legacy_seq2seq.sequence_loss(logits, targets, weights, average_across_timesteps=True, average_across_batch=True, softmax_loss_function=None, name=None)
I went through the tensorflow implementation. Through the perplexity has some broad meaning here in this function perplexity means
two to the power of your total cross entropy loss.
Please refer the first answer of this question.