Hello there,

I admire your work and it took me some time to wrap my head around your [algorithm] (https://github.com/sourcedexter/tfClassifier/blob/master/text_classification/classify_text.py) 2nd loop to be particular.

The two nested loops I've found very costly, I haven't calculated the complexity but it seems that it might reach O(N^2) at times. I have 300k rows of data with text cells that represent "descriptions of certain categories" more than 50 words, so I am looking for approaches to manufacture a bag of words in a much smaller amount of time.

Thanks!

What happens when you train the model in one file and try to use it from another in another time. looks like the code needs the variable "words" created in the nested loop to predict the class.

When I have exported it to tensorflow serving, it is deployed and ready to server.
But when we are consuming that service through one python client, it is returning ('Result is: ', outputs {
key: "prediction"
value {
dtype: DT_FLOAT
tensor_shape {
dim {
size: 1
}
dim {
size: 2048
}
}
float_val: 0.317088961601
float_val: 0.0552041605115
float_val: 0.778943479061
float_val: 0.340197831392
float_val: 0.0894310623407
}
I'm not able figure it out, what was the issue. I'm expecting result like /label_image.py.
Could you please guide me on this.
Thanks

Hi and thanks for sharing this. I have retrained a new model instance with a new set of images (5 classes). Any advice on how can be used to predict/make inference on my test set images ? i.e. is there a way for the script retrain_model_classifier.py to accept a whole directory of images ?

Also what modifications do we need to make to save the retrained model as .h5 at the end of the training?

Thank you in advance

I'm following the documentation on https://sourcedexter.com/retrain-tensorflow-inception-model/ but I keep running into an error on retraining.

The tensor <tf.Tensor 'pool_3/_reshape:0' shape=(1, 2048) dtype=float32> cannot be accessed from here, because it was defined in <tensorflow.python.framework.ops.Graph object at 0x000001A3E4EAC648>, which is out of scope.

Any idea on how to deal with this?

i already have installed python 3.5

Currently tfClassifier can load 8 CPUs by default.
Suggest to add a --cpu-number flag, for example, --cpu-number=32 will help the program fully use the power of a 32 core server.

anyway, love this project.

Thank you.

Can you please tell me the versions used..
I am facing many incompatibilities
Using tensorflow version 1.13.1
can u guide with version of
tensorflow and tflearn

How to optimize the training model on the existing model?

Hi There,

I use the following for training, it works well:
python retrain_new.py --image_dir ./DataSet --output_graph ./output_dir/output_graph.pb --output_labels ./output_dir/output_labels.txt --summaries_dir ./output_dir/retrain_logs --how_many_training_steps 600 --learning_rate 0.01 --testing_percentage 10 --validation_percentage 10 --model_dir ./inception --bottleneck_dir ./output_dir

When I run the following to do the classfiying test:
python retrain_model_classifier.py ./test_img/2222.jpg

It raise the following error:
Traceback (most recent call last): File "retrain_model_classifier.py", line 12, in <module> in tf.gfile.GFile("./labels.txt")] File "retrain_model_classifier.py", line 11, in <listcomp> label_lines = [line.rstrip() for line File "D:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 220, in __next__ return self.next() File "D:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 214, in next retval = self.readline() File "D:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 183, in readline self._preread_check() File "D:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 85, in _preread_check compat.as_bytes(self.__name), 1024 * 512, status) File "D:\ProgramData\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 519, in __exit__ c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: ./labels.txt : ϵͳ\udcd5Ҳ\udcbb\udcb5\udcbdָ\udcb6\udca8\udcb5\udcc4\udcceļ\udcfe\udca1\udca3 ; No such file or directory

I guess I missed some arguments when running retrain_model_classifier.py

Can you pls help on this?

Hi, I'm retraining the image classifier model and I want to plot the output of each hidden layer to check the interesting feature. How can I do that?
Thanks!

Hii,

I was able to use this code for my project and it turned out to be very useful.
Thanks a ton.

However, I wanted to know how to load and restore this DNN model. Tried a lot of other methods but none worked.
Could you kindly help as I wanted to deploy it as early as possible.

Sir,I have trained a model on my own data which is for flower classification,and it has three classes, that is azalea,tulip and lily,and now I want to use the model to classify them,so How to use the model to classify the data,the speed I need is about 100fps,and the model I use is mobilenet,and I have tried to modify the code in tensorflow :tensorflow/tensorflow/examples/label_image/label_image.py,but I failed,could you please help me?

As we known, the tensorflow changed quiet greatly between different version.

Can you pls tell which version I need to choose to run this model(images classifier)?