Tijmen

I am currently trying to perform training using the GPU as-well, however I am experiencing different issues than those listed above. My issue is that at a certain step in...

Hey @Grieverheart I mostly tested it with the deferred.py sample, so maybe try that one :)

@Grieverheart I updated the samples to tf 2.4.1 and fixed some issues saving images. However all 3 samples produced correct results for me as can be seen in these images:...

Could you be more specific with your question? Maybe post an error code or try to explain why you suspect there is a problem with downloading model parameters?

Training an object detector from scratch is possible but not trivial, have a look at this paper: [DSOD: Learning Deeply Supervised Object Detectors from Scratch](https://arxiv.org/abs/1708.01241) It is not possible to...

Short answer: You can but it is difficult, it is easier to add this line when a training is finished: tf.train.write_graph(sess.graph_def, "/tmp/load", "test.pb", False) #proto Example from: https://github.com/tensorflow/tensorflow/issues/616 ``` import...

That boolean determines whether or not to write the file as binary or as text https://www.tensorflow.org/api_docs/python/tf/train/write_graph It has a default value (True) so you don't need to set it.

Found this blog post. https://blog.metaflow.fr/tensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3adc It might be pretty straight forward after all, worth looking into. I still recommend outputting the .pb file directly from training but this should work...

When you say usage do you mean memory usage or gpu computation utilisation? In the first case the reason that you don't see a difference could be because with such...

Check out this git repository: https://github.com/DeepScale/SqueezeNet Squeezedet builds upon this network by adding fire 10, fire 11 and conv12 and structure for the loss function. So that might be a...