Right now I am using yolo3 but it does not have all 9000 classes.
Is it possible to use yolo3 with yolo9000 classes and weights?
I would like to have as many objects as possible to assign tags to some pictures and I am not sure if I should use yolo9000 or it is possible to use yolo3 with 9000 classes.
Update:
So, I tired loading the weights yolo9000 with yolo3 and the model does not find any objects. It seems I need to tweak something else.
Got it,
I needed to change thresholds when I call detect, default value is 0.5
https://github.com/pjreddie/darknet/blob/61c9d02ec461e30d55762ec7669d6a1d3c356fb2/python/darknet.py#L125
det = darknet.detect(self._net, self._meta, im, thresh=.1, hier_thresh=.1, **kwargs)
Related
I use keras fit() method with custom metrics passed to model.
The metrics are stateful - i.e. are a subclass of a Metric, as described in https://keras.io/api/metrics/#as-subclasses-of-metric-stateful
When I run the code in a multi-gpu environment using a tf.distribute.MirroredStrategy() my metric code is called on every GPU separately with batch_size/no_of_gpus examples passed, which is reasonable to expect.
What happens next is that multiple scalars (one from every GPU) of the metric value need to be reduced to a single scalar, and what I get all the time is a sum reduction, while I would like to control that.
Keep in mind, that reduction parameter is the one of Loss in keras, and there is no such thing in the Metric class: https://github.com/tensorflow/tensorflow/blob/acbc065f8eb2ed05c7ab5c42b5c5bd6abdd2f91f/tensorflow/python/keras/metrics.py#L87
(the only crazy thing I tried was to inherit from a Mean class that is a subclass of a Metric but that didn't change anything)
reduction is mentioned in the metrics code, however this is a reduction over multiple accumulated values in a single metric object, and in multi-gpu setting - this is not the case, as every metric works in its own GPU and is somehow aggregated at the end.
The way I debugged it to understand this behaviour was - I was printing the shapes and the results inside update_state method of the metric. And then I looked at value of the metric in logs object in on_batch_end callback.
I tried looking at TF code, but couldn't find the place this is happening.
I would like to be able to control this behaviour - so either pick 'mean' or 'sum' for the metric, or at least know where it is being done in the code.
Edited: I guess this https://github.com/tensorflow/tensorflow/issues/39268 sheds some more light on this issue
I am facing the same problem as you (and that's why I found your question).
Seeing that it's been 15 days since you asked the question and there are no answers/comments yet, I thought I might share my temporary workaround.
Like you, I also think that a SUM reduction has been performed when combining progress over multiple GPUs. What I did is to pass the number of GPUs (e.g. given by the num_replicas_in_sync attribute of your tf.distribute strategy object) into the __init__(...) constructor of your sub-classed metric object, and use it to divide the return value in the results() method.
Potentially, you could also use tf.distribute.get_strategy() from within the metric object to make it "strategy aware", and use the information to decide how to modify the values in an ad hoc manner so that the SUM reduction will produce what you want.
I hope this helps for now, whether as a suggestion or as a confirmation that you're not alone on this.
When implementing the subclass of the Keras Metric class, you have to override the merge_state() function correctly. If you do not override this function, the default implementation will be used - which is a simple sum.
See: https://www.tensorflow.org/api_docs/python/tf/keras/metrics/Metric
I successfully managed to implement learning to rank by following the tutorial TF-Ranking for sparse features using the ANTIQUE question answering dataset.
Now my goal is to successfully save the learned model to disk so that I can easily load it without training again. Due to the Tensorflow docs, the estimator.export_saved_model() method seems to be the way to go. But I can't wrap my head around how to tell Tensorflow how my feature structure looks like. Due to the docs here the easiest way seems to be calling tf.estimator.export.build_parsing_serving_input_receiver_fn(), which returns me the required inpur receiver function which I have to pass to the export_saved_model function. But how do I tell Tensorflow how my features from my learning to rank model look like?
From my current understanding the model has context feature specs and example feature specs. So I guess I somehow have to combine those two specs into one feature description, which I then can pass to the build_parsing_serving_input_receiver_fn function?
So I think you are on the right track;
You can get a build_ranking_serving_input_receiver_fn like this: (substitue context_feature_columns(...) and example_feature_columns(...) with defs you probably have for creating your own context and example structures for your training data):
def example_serving_input_fn():
context_feature_spec = tf.feature_column.make_parse_example_spec(
context_feature_columns(_VOCAB_PATHS).values())
example_feature_spec = tf.feature_column.make_parse_example_spec(
list(example_feature_columns(_VOCAB_PATHS).values()))
servingInputReceiver = tfr.data.build_ranking_serving_input_receiver_fn(
data_format=tfr.data.ELWC,
context_feature_spec=context_feature_spec,
example_feature_spec=example_feature_spec,
list_size=_LIST_SIZE,
receiver_name="input_ranking_data",
default_batch_size=None)
return servingInputReceiver
And then pass this to export_saved_model like this:
ranker.export_saved_model('path_to_save_model', example_serving_input_fn())
(ranker here is a tf.estimator.Estimator, maybe you called this 'estimator' in your code)
ranker = tf.estimator.Estimator(
model_fn=model_fn,
model_dir=_MODEL_DIR,
config=run_config)
When training a single class object detector in Tensorflow, I am trying to pass instances of images where no signal object exists, such that the model doesn't learn that every image contains at least one instance of that class. E.g. if my signal were cats, id want to pass pictures of other animals/landscapes as background -this could also reduce false positives.
I can see that a class id is reserved in the object detection API (0) for background, but I am unsure how to code this into the TFrecords for my background images - class could be 0 but what would be the bounding box coords? Or do i need a simpler classifier on top of this model to detect if there is a signal in the image or not, prior to detecting position?
Later approach of simple classifier, makes sense. I don't think there is a way to do the first part. You can use check on confidence score as well apart from checking the object is present.
It is good practice to create a dataset with not objects of interest, for the same you need to use the same tools (like - label img) that you have used for adding the boxes, image with no BB wil have xml files with no details of BB but only details of the image. The script create tf record will create the tf record from the xml files, look at the below links for more inforamtion -
Create tf record example -
https://github.com/tensorflow/models/blob/master/research/object_detection/dataset_tools/create_pet_tf_record.py
Using your own dataset-
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/using_your_own_dataset.md
I have written a custom data iterator using mx.io.DataIter class. What's the easiest way to use this data iterator with Gluon interface?
I went through the documentation and couldn't find an easy way to do so. One of my idea was to use it as iterator and get data adn label from each batch as follows.
for e in range(epochs):
train_iter.reset()
for batch_data in train_iter:
data = nd.concatenate(([d for d in batch_data.data]))
label = nd.concatenate(([l for l in batch_data.label]))
with autograd.record():
output = net(data)
loss = softmax_cross_entropy(output, label)
loss.backward()
trainer.step(batch_size)
print(nd.mean(loss).asscalar())
But this may not be optimal as I need to concatenate per batch.
What's the optimal way to achieve this? i.e. is there a systematic
way to write a simple custom iterator for gluon?
How do I add context information in above cases?
I think your approach works. Basically you can get data from batch_data.data and label from batch_data.label and feed them into the network.
I'm not sure why you need to concat the data and labels - maybe it's to do with your network definition.
If you ever need to split the data and train on multiple GPUs, you can use the gluon.utils.split_and_load function to do that.
I'm working on a project which needs to evaluate the performance of CNN/RNN after adding noise to all the variables. For example, if we have an simple MLP, I want to add a random gaussian noise to all the weight parameters, which is not difficult. However, it doesn't seem easy to manipulate the variables for RNN. For example, the variables inside the tf.contrib.rnn.BasicLSTMCell are encapsulated and not accessble for users.
I found a possible way to do this by using the tf.train.saver() function. I can print all the variables including the encapsulated variables. However, how to modify the value of all the variables is still not clear.
Is there an easy way to do this?
You can use tf.trainable_variables (doc) or tf.global_variables (doc) to get those variables, and add noisy to them.