Hey @adamkusey
I read your medium article related to this repo code. It's fantastic.
I was trying to a dry run on your lstm model, but couldn't understand what this file dev-access.csv must have in order to do the prediction on a request log entry?

Model: "sequential_7"

Layer (type) Output Shape Param #

embedding_7 (Embedding) (None, 1024, 32) 2016

dropout_14 (Dropout) (None, 1024, 32) 0

lstm_7 (LSTM) (None, 64) 24832

dropout_15 (Dropout) (None, 64) 0

dense_7 (Dense) (None, 1) 65

Total params: 26,913
Trainable params: 26,913
Non-trainable params: 0

None
Traceback (most recent call last):

File "", line 94, in
train(csv_file)

File "", line 71, in train
model.fit(X_train, Y_train, validation_split=0.25, epochs=3, batch_size=128, callbacks=[tb_callback])

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 728, in fit
use_multiprocessing=use_multiprocessing)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 224, in fit
distribution_strategy=strategy)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 528, in _process_training_inputs
distribution_strategy=distribution_strategy)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\data_adapter.py", line 321, in init
dataset_ops.DatasetV2.from_tensors(inputs).repeat()

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\data\ops\dataset_ops.py", line 414, in from_tensors
return TensorDataset(tensors)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\data\ops\dataset_ops.py", line 2335, in init
element = structure.normalize_element(element)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\data\util\structure.py", line 111, in normalize_element
ops.convert_to_tensor(t, name="component_%d" % i))

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1184, in convert_to_tensor
return convert_to_tensor_v2(value, dtype, preferred_dtype, name)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1242, in convert_to_tensor_v2
as_ref=False)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1296, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\tensor_conversion_registry.py", line 52, in _default_conversion_function
return constant_op.constant(value, dtype, name=name)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 227, in constant
allow_broadcast=True)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 235, in _constant_impl
t = convert_to_eager_tensor(value, ctx, dtype)

File "C:\Anaconda3\lib\site-packages\tensorflow_core\python\framework\constant_op.py", line 96, in convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int).

Layer (type) Output Shape Param #

embedding_2 (Embedding) (None, 1024, 32) 2016

dropout_3 (Dropout) (None, 1024, 32) 0

lstm_2 (LSTM) (None, 64) 24832

dropout_4 (Dropout) (None, 64) 0

dense_2 (Dense) (None, 1) 65

Total params: 26,913
Trainable params: 26,913
Non-trainable params: 0

None
Train on 15059 samples, validate on 5020 samples
Epoch 1/3
15059/15059 [==============================] - 215s 14ms/step - loss: 0.6129 - acc: 0.6508 - val_loss: 0.2914 - val_acc: 0.9309

ValueError Traceback (most recent call last)
in ()
82
83 csv_file = '/content/dev-access.csv'
---> 84 train(csv_file)

in train(csv_file)
63 model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
64 print(model.summary())
---> 65 model.fit(X_train, Y_train, validation_split=0.25, epochs=3, batch_size=128, callbacks=[tb_callback])
66
67 # Evaluate model

/usr/local/lib/python3.6/dist-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
1037 initial_epoch=initial_epoch,
1038 steps_per_epoch=steps_per_epoch,
-> 1039 validation_steps=validation_steps)
1040
1041 def evaluate(self, x=None, y=None,

/usr/local/lib/python3.6/dist-packages/keras/engine/training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
215 for l, o in zip(out_labels, val_outs):
216 epoch_logs['val_' + l] = o
--> 217 callbacks.on_epoch_end(epoch, epoch_logs)
218 if callback_model.stop_training:
219 break

/usr/local/lib/python3.6/dist-packages/keras/callbacks.py in on_epoch_end(self, epoch, logs)
77 logs = logs or {}
78 for callback in self.callbacks:
---> 79 callback.on_epoch_end(epoch, logs)
80
81 def on_batch_begin(self, batch, logs=None):

/usr/local/lib/python3.6/dist-packages/keras/callbacks.py in on_epoch_end(self, epoch, logs)
913 "provided, and cannot be a generator.")
914 if self.embeddings_data is None and self.embeddings_freq:
--> 915 raise ValueError("To visualize embeddings, embeddings_data must "
916 "be provided.")
917 if self.validation_data and self.histogram_freq:

ValueError: To visualize embeddings, embeddings_data must be provided.

raise ValueError("To visualize embeddings, embeddings_data must "
ValueError: To visualize embeddings, embeddings_data must be provided.