Hello, I was trying to apply your code on my Windows machine. It seems that the code works perfectly fine, here are the last few lines when I run the app.py file (e.g. locally) in my Windows shell:

Restoring parameters from results/crf/model.weights/
 * Debugger is active!
 * Debugger PIN: 740-578-024
 * Running on http://0.0.0.0:5000/ (Press CTRL+C to quit)

Unfortunately, when I visit the IP address printed in the terminal, it says "unable to connect" (see the first attached image)

Changing to my local IP address, which is http://127.0.0.1:5000/, i can connect but the only thing I can see are the two words "Index API" in the top left corner (see the second attached image).

Do you think it is Windows related or am I doing something wrong?

image one:

image two:

When I tried to execute python app.py, I get following error message.

Traceback (most recent call last):
File "/Users/admin/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1022, in _do_call
return fn(*args)
File "/Users/admin/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1004, in _run_fn
status, run_metadata)
File "/Users/admin/anaconda/lib/python3.6/contextlib.py", line 89, in exit
next(self.gen)
File "/Users/admin/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 469, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.NotFoundError: Key bi-lstm/bidirectional_rnn/bw/lstm_cell/biases not found in checkpoint
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

During handling of the above exception, another exception occurred:

When completing this project using TF2 many functions in base_model can't work due to TF2 not using Sessions. In serve.py the function restore_session() is called, what changes should be made to the code to do this in TF2.

I have tried
checkpoint_path = "training_3/cp.ckpt"#defining path where weights will be saved
checkpoint_dir = os.path.dirname(checkpoint_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_weights_only=True,
verbose=1)#defining a function that is called in my model.fit by using: callbacks=[cp_callback])

I can then call load_weights but I am struggling with doing this within the get_model_api() in serve.py
Any help with this issue would be great, thanks.

Is there a concurrency issue with calling the model interface directly in the flask? For example, when multiple clients call the interface at the same time, the model performs multiple operations at the same time.

PS C:\Users\RiyazHussain\Downloads\api_ner-master\api_ner-master> python app.py
2022-05-19 12:38:52.702197: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-05-19 12:38:52.702526: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
File "C:\Users\RiyazHussain\Downloads\api_ner-master\api_ner-master\app.py", line 23, in
model_api = get_model_api()
File "C:\Users\RiyazHussain\Downloads\api_ner-master\api_ner-master\serve.py", line 40, in get_model_api
model.build()
File "C:\Users\RiyazHussain\Downloads\api_ner-master\api_ner-master\model\ner_model.py", line 220, in build
self.add_placeholders()
File "C:\Users\RiyazHussain\Downloads\api_ner-master\api_ner-master\model\ner_model.py", line 24, in add_placeholders
self.word_ids = tf.placeholder(tf.int32, shape=[None, None],
AttributeError: module 'tensorflow' has no attribute 'placeholder'
PS C:\Users\RiyazHussain\Downloads\api_ner-master\api_ner-master>