scripts/.ipynb_checkpoints/testing-checkpoint.ipynb

+%% Cell type:code id: tags:
+
+``` python
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import BatchNormalization
+from tensorflow.keras.layers import SeparableConv2D
+from tensorflow.keras.layers import MaxPooling2D
+from tensorflow.keras.layers import Activation
+from tensorflow.keras.layers import Flatten
+from tensorflow.keras.layers import Dropout
+from tensorflow.keras.layers import Dense
+
+import matplotlib
+matplotlib.use("Agg")
+# import the necessary packages
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.optimizers import SGD
+from tensorflow.keras.utils import to_categorical
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+# from imutils import paths
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import tensorflow as tf
+# from imutils import paths
+
+# import the necessary packages
+
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import pandas as pd
+import keras
+import tempfile
+from tensorflow.keras.callbacks import LambdaCallback
+physical_devices = tf.config.experimental.list_physical_devices('GPU')
+# physical_devices = tf.config.experimental.list_physical_device
+
+tf.config.experimental.set_memory_growth(physical_devices[0], True)
+assert tf.config.experimental.get_memory_growth(physical_devices[0])
+import keras
+from keras import backend as K
+# K.tensorflow_backend._get_available_gpus()
+from tensorflow.python.client import device_lib
+print(device_lib.list_local_devices())
+
+dataDirectoryTrain = "/userdata/kerasData/preloaded/flowDirectory2/train/"
+dataDirectoryValidation = "/userdata/kerasData/preloaded/flowDirectory2/validation/"
+dataDirectoryTest = "/userdata/kerasData/preloaded/flowDirectory2/test/"
+
+TRAIN_SPLIT = 0.75
+TEST_SPLIT = 0.25
+INIT_LR = 1e-2
+BATCH_SIZE = 8
+NUM_EPOCHS = 50
+image_size = 2048,1536
+class_mode = "categorical"
+
+image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0.15,
+    width_shift_range=0.2,
+    height_shift_range=0.2,
+    shear_range=0.15,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+
+image_generatorCLASSIC = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0,
+    width_shift_range=0,
+    height_shift_range=0,
+    shear_range=0,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+
+trainingGeneratorHPWREN = image_generator.flow_from_directory(
+    dataDirectoryTrain,
+    target_size=image_size,
+    seed=42,
+    batch_size=BATCH_SIZE,
+    class_mode=class_mode,
+    subset="training")
+
+validationGeneratorHPWREN = image_generator.flow_from_directory(
+    dataDirectoryValidation,
+    target_size=image_size,
+    batch_size=BATCH_SIZE,
+    seed=42,
+    class_mode=class_mode,
+    subset = "training")
+
+testGeneratorHPWREN = image_generatorCLASSIC.flow_from_directory(
+    dataDirectoryTest,
+    target_size=image_size,
+    batch_size=BATCH_SIZE,
+    seed=42,
+    class_mode=class_mode,
+    subset = "training")
+
+def f1(y_true, y_pred):
+
+    def recall(y_true, y_pred):
+        """Recall metric.
+
+        Only computes a batch-wise average of recall.
+
+        Computes the recall, a metric for multi-label classification of
+        how many relevant items are selected.
+        """
+        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
+        recall = true_positives / (possible_positives + K.epsilon())
+        return recall
+
+    def precision(y_true, y_pred):
+        """Precision metric.
+
+        Only computes a batch-wise average of precision.
+
+        Computes the precision, a metric for multi-label classification of
+        how many selected items are relevant.
+        """
+        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
+        precision = true_positives / (predicted_positives + K.epsilon())
+        return precision
+    precision = precision(y_true, y_pred)
+    recall = recall(y_true, y_pred)
+    return 2*((precision*recall)/(precision+recall+K.epsilon()))
+
+```
+
+%% Output
+
+    [name: "/device:CPU:0"
+    device_type: "CPU"
+    memory_limit: 268435456
+    locality {
+    }
+    incarnation: 12397120884647711703
+    , name: "/device:XLA_CPU:0"
+    device_type: "XLA_CPU"
+    memory_limit: 17179869184
+    locality {
+    }
+    incarnation: 7450379519501849834
+    physical_device_desc: "device: XLA_CPU device"
+    , name: "/device:XLA_GPU:0"
+    device_type: "XLA_GPU"
+    memory_limit: 17179869184
+    locality {
+    }
+    incarnation: 9162883243846547682
+    physical_device_desc: "device: XLA_GPU device"
+    , name: "/device:GPU:0"
+    device_type: "GPU"
+    memory_limit: 23695670656
+    locality {
+      bus_id: 2
+      numa_node: 1
+      links {
+      }
+    }
+    incarnation: 5784131758698526549
+    physical_device_desc: "device: 0, name: TITAN RTX, pci bus id: 0000:86:00.0, compute capability: 7.5"
+    ]
+    Found 648 images belonging to 2 classes.
+    Found 243 images belonging to 2 classes.
+    Found 239 images belonging to 2 classes.
+
+%% Cell type:code id: tags:
+
+``` python
+class FireDetectionNet:
+    @staticmethod
+    def build(width, height, depth):
+        # initialize the model along with the input shape to be
+        # "channels last" and the channels dimension itself
+        model = Sequential()
+        inputShape = (height, width, depth)
+        chanDim = -1
+
+        model.add(SeparableConv2D(16, (7, 7), padding="same",
+                                  input_shape=inputShape))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+
+        model.add(SeparableConv2D(32, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+
+        model.add(SeparableConv2D(64, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(SeparableConv2D(64, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+
+        model.add(Flatten())
+        model.add(Dense(128))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization())
+        model.add(Dropout(0.5))
+
+        # second set of FC => RELU layers
+        model.add(Dense(128))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization())
+        model.add(Dropout(0.5))
+
+        # softmax classifier
+        model.add(Dense(2))
+        model.add(Activation("softmax"))
+
+        # return the constructed network architecture
+        return model
+
+# name = "HPWRENGroundUp_2048_V1_BATCH"
+# opt = SGD(lr=INIT_LR, momentum=0.9,
+#     decay=INIT_LR / NUM_EPOCHS)
+# groundUpModel = FireDetectionNet.build(width=2048, height=1536, depth=3)
+# groundUpModel.compile(loss="binary_crossentropy", optimizer=opt,
+# metrics=["accuracy", tf.keras.metrics.Precision(), tf.keras.metrics.Recall(), f1])
+# mc = tf.keras.callbacks.ModelCheckpoint(f'/userdata/kerasData/pyimagesearch/output/experimental/{name}HPWREN.model',
+# monitor='val_loss', mode='auto',  save_freq='epoch', verbose=1)
+# early_stopping_callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=20)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+testModel = FireDetectionNet.build(1536,2048,3)
+testModel.summary()
+```
+
+%% Output
+
+    Model: "sequential_1"
+    _________________________________________________________________
+    Layer (type)                 Output Shape              Param #
+    =================================================================
+    separable_conv2d_4 (Separabl (None, 2048, 1536, 16)    211
+    _________________________________________________________________
+    activation_7 (Activation)    (None, 2048, 1536, 16)    0
+    _________________________________________________________________
+    batch_normalization_6 (Batch (None, 2048, 1536, 16)    64
+    _________________________________________________________________
+    max_pooling2d_3 (MaxPooling2 (None, 1024, 768, 16)     0
+    _________________________________________________________________
+    separable_conv2d_5 (Separabl (None, 1024, 768, 32)     688
+    _________________________________________________________________
+    activation_8 (Activation)    (None, 1024, 768, 32)     0
+    _________________________________________________________________
+    batch_normalization_7 (Batch (None, 1024, 768, 32)     128
+    _________________________________________________________________
+    max_pooling2d_4 (MaxPooling2 (None, 512, 384, 32)      0
+    _________________________________________________________________
+    separable_conv2d_6 (Separabl (None, 512, 384, 64)      2400
+    _________________________________________________________________
+    activation_9 (Activation)    (None, 512, 384, 64)      0
+    _________________________________________________________________
+    batch_normalization_8 (Batch (None, 512, 384, 64)      256
+    _________________________________________________________________
+    separable_conv2d_7 (Separabl (None, 512, 384, 64)      4736
+    _________________________________________________________________
+    activation_10 (Activation)   (None, 512, 384, 64)      0
+    _________________________________________________________________
+    batch_normalization_9 (Batch (None, 512, 384, 64)      256
+    _________________________________________________________________
+    max_pooling2d_5 (MaxPooling2 (None, 256, 192, 64)      0
+    _________________________________________________________________
+    flatten_1 (Flatten)          (None, 3145728)           0
+    _________________________________________________________________
+    dense_3 (Dense)              (None, 128)               402653312
+    _________________________________________________________________
+    activation_11 (Activation)   (None, 128)               0
+    _________________________________________________________________
+    batch_normalization_10 (Batc (None, 128)               512
+    _________________________________________________________________
+    dropout_2 (Dropout)          (None, 128)               0
+    _________________________________________________________________
+    dense_4 (Dense)              (None, 128)               16512
+    _________________________________________________________________
+    activation_12 (Activation)   (None, 128)               0
+    _________________________________________________________________
+    batch_normalization_11 (Batc (None, 128)               512
+    _________________________________________________________________
+    dropout_3 (Dropout)          (None, 128)               0
+    _________________________________________________________________
+    dense_5 (Dense)              (None, 2)                 258
+    _________________________________________________________________
+    activation_13 (Activation)   (None, 2)                 0
+    =================================================================
+    Total params: 402,679,845
+    Trainable params: 402,678,981
+    Non-trainable params: 864
+    _________________________________________________________________
+
+%% Cell type:code id: tags:
+
+``` python
+e8Modeladdress = "/userdata/kerasData/pyimagesearch/output/experimental/HPWRENGroundUp_e8_2048_SPLIT1_v1HPWREN.model"
+e7Modeladdress = "/userdata/kerasData/pyimagesearch/output/experimental/HPWRENGroundUp_e8_2048_SPLIT1_v2_e7HPWREN.model"
+e6Modeladdress = "/userdata/kerasData/pyimagesearch/output/experimental/HPWRENGroundUp_2048_SPLIT1_v3_e6HPWREN.model"
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# model = FireDetectionNet.build(width=2048, height=1536, depth=3)
+# model.load_weights(e8Modeladdress)
+attempt = tf.saved_model.load(e8Modeladdress)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e8model = tf.keras.models.load_model(e8Modeladdress,custom_objects={"f1":f1})
+e7model = tf.keras.models.load_model(e7Modeladdress,custom_objects={"f1":f1})
+e6model = tf.keras.models.load_model(e6Modeladdress,custom_objects={"f1":f1})
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e8model.evaluate(testGeneratorHPWREN)
+```
+
+%% Output
+
+    30/30 [==============================] - 338s 11s/step - loss: 0.8079 - accuracy: 0.4351 - precision: 0.4351 - recall: 0.4351 - f1: 0.4351
+
+    [0.8078833818435669,
+     0.4351464509963989,
+     0.4351464509963989,
+     0.4351464509963989,
+     0.43511903285980225]
+
+%% Cell type:code id: tags:
+
+``` python
+e7model.evaluate(testGeneratorHPWREN)
+```
+
+%% Output
+
+    30/30 [==============================] - 239s 8s/step - loss: 0.8104 - accuracy: 0.5397 - precision: 0.5397 - recall: 0.5397 - f1: 0.5393
+
+    [0.8103770613670349,
+     0.5397489666938782,
+     0.5397489666938782,
+     0.5397489666938782,
+     0.5392856597900391]
+
+%% Cell type:code id: tags:
+
+``` python
+e6model.evaluate(testGeneratorHPWREN)
+```
+
+%% Output
+
+    30/30 [==============================] - 242s 8s/step - loss: 0.8597 - accuracy: 0.4728 - precision: 0.4728 - recall: 0.4728 - f1: 0.4720
+
+    [0.8597329258918762,
+     0.47280335426330566,
+     0.47280335426330566,
+     0.47280335426330566,
+     0.47202378511428833]
+
+%% Cell type:code id: tags:
+
+``` python
+%matplotlib inline
+lrs = LRfINDER.lrs[10:-1]
+losses = LRfINDER.losses[10:-1]
+plt.plot(lrs, losses)
+plt.xscale("log")
+plt.xlabel("Learning Rate (Log Scale)")
+plt.ylabel("Loss")
+```
+
+%% Output
+
+    Text(0, 0.5, 'Loss')
+
+
+
+%% Cell type:code id: tags:
+
+``` python
+image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0.15,
+    width_shift_range=0.2,
+    height_shift_range=0.2,
+    shear_range=0.15,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+```
+
+%% Cell type:code id: tags:
+
+``` python
+testImage = image_generator.flow_from_("/userdata/kerasData/preloaded/flowDirectory2/test/fire/1512676696_+02100.jpg")))
+```
+
+%% Cell type:code id: tags:
+
+``` python
+testImage.shape
+```
+
+%% Output
+
+    (1536, 2048, 3)
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e6model.predict(testImage)
+```
+
+%% Output
+
+    ---------------------------------------------------------------------------
+    ValueError                                Traceback (most recent call last)
+    <ipython-input-48-d3b35444c1d2> in <module>
+    ----> 1 e6model.predict(testImage)
+
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
+         86       raise ValueError('{} is not supported in multi-worker mode.'.format(
+         87           method.__name__))
+    ---> 88     return method(self, *args, **kwargs)
+         89
+         90   return tf_decorator.make_decorator(
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
+       1266           for step in data_handler.steps():
+       1267             callbacks.on_predict_batch_begin(step)
+    -> 1268             tmp_batch_outputs = predict_function(iterator)
+       1269             # Catch OutOfRangeError for Datasets of unknown size.
+       1270             # This blocks until the batch has finished executing.
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
+        578         xla_context.Exit()
+        579     else:
+    --> 580       result = self._call(*args, **kwds)
+        581
+        582     if tracing_count == self._get_tracing_count():
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
+        625       # This is the first call of __call__, so we have to initialize.
+        626       initializers = []
+    --> 627       self._initialize(args, kwds, add_initializers_to=initializers)
+        628     finally:
+        629       # At this point we know that the initialization is complete (or less
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
+        504     self._concrete_stateful_fn = (
+        505         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
+    --> 506             *args, **kwds))
+        507
+        508     def invalid_creator_scope(*unused_args, **unused_kwds):
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
+       2444       args, kwargs = None, None
+       2445     with self._lock:
+    -> 2446       graph_function, _, _ = self._maybe_define_function(args, kwargs)
+       2447     return graph_function
+       2448
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
+       2775
+       2776       self._function_cache.missed.add(call_context_key)
+    -> 2777       graph_function = self._create_graph_function(args, kwargs)
+       2778       self._function_cache.primary[cache_key] = graph_function
+       2779       return graph_function, args, kwargs
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
+       2665             arg_names=arg_names,
+       2666             override_flat_arg_shapes=override_flat_arg_shapes,
+    -> 2667             capture_by_value=self._capture_by_value),
+       2668         self._function_attributes,
+       2669         # Tell the ConcreteFunction to clean up its graph once it goes out of
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
+        979         _, original_func = tf_decorator.unwrap(python_func)
+        980
+    --> 981       func_outputs = python_func(*func_args, **func_kwargs)
+        982
+        983       # invariant: `func_outputs` contains only Tensors, CompositeTensors,
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
+        439         # __wrapped__ allows AutoGraph to swap in a converted function. We give
+        440         # the function a weak reference to itself to avoid a reference cycle.
+    --> 441         return weak_wrapped_fn().__wrapped__(*args, **kwds)
+        442     weak_wrapped_fn = weakref.ref(wrapped_fn)
+        443
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
+        966           except Exception as e:  # pylint:disable=broad-except
+        967             if hasattr(e, "ag_error_metadata"):
+    --> 968               raise e.ag_error_metadata.to_exception(e)
+        969             else:
+        970               raise
+    ValueError: in user code:
+
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:1147 predict_function  *
+        outputs = self.distribute_strategy.run(
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
+        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
+        return self._call_for_each_replica(fn, args, kwargs)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
+        return fn(*args, **kwargs)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:1122 predict_step  **
+        return self(x, training=False)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py:886 __call__
+        self.name)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/input_spec.py:180 assert_input_compatibility
+        str(x.shape.as_list()))
+
+    ValueError: Input 0 of layer sequential is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [32, 2048, 3]

scripts/README.md

+# Scrips for classifcation algorythms 
+The scrips and notebooks within this directory are everything needed to download the images from HJPWREN and design & test the classifcation algorythms 
+
+## Explanations
+
+- getFiles.sh: Code used to download the HPWREN archieve to current directory
+Just run this shell file at the place you want the directory to be
+
+- imageLoader.ipynb: Used to sort the HPWREN archieve into (training, testing, validation) subdirectories that Keras can read
+<br> ![test](scripts/scripts/getPath.PNG) <br />
+Set the mypath to the current location of the HPWREN archieve (filtered)
+Set savepath to the directory you want the sorted data archieve (with training, validation, and test )
+
+- trainingScript.py: Used to define the model and use it to train on the subdirectories that was previously created
+<br> ![test](scripts/scripts/training.PNG)<br />
+Assign all the subdirectories 
+<br>![test](scripts/scripts/training2.PNG)<br />
+This is the location where the model will be saved
+<br>![test](scripts/scripts/training3.PNG)<br />
+This is the location where the training history will be saved
+
+- historyEvaluator.ipynb: Used to see the training loss and other metrics of training done of script
+<br>![test](scripts/scripts/results.PNG)<br />
+Assign this to where the training history was saved (above)
+
+- testing.ipynb: Used to test new model on training subset
\ No newline at end of file

scripts/e5_2048Training.py

+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import BatchNormalization
+from tensorflow.keras.layers import SeparableConv2D
+from tensorflow.keras.layers import MaxPooling2D
+from tensorflow.keras.layers import Activation
+from tensorflow.keras.layers import Flatten
+from tensorflow.keras.layers import Dropout
+from tensorflow.keras.layers import Dense
+
+
+import matplotlib
+matplotlib.use("Agg") 
+# import the necessary packages
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.optimizers import SGD
+from tensorflow.keras.utils import to_categorical
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+# from imutils import paths
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import matplotlib
+matplotlib.use("Agg")
+ 
+# import the necessary packages
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.optimizers import SGD
+from tensorflow.keras.utils import to_categorical
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+
+# from imutils import paths
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import tensorflow as tf
+from os import listdir
+from os.path import isdir, join, isfile
+from numpy import asarray
+from numpy import save
+import itertools
+
+import matplotlib
+matplotlib.use("Agg")
+ 
+# import the necessary packages
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.optimizers import SGD
+from tensorflow.keras.utils import to_categorical
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+# from imutils import paths
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import pandas as pd
+import keras
+import tempfile
+from tensorflow.keras.callbacks import LambdaCallback
+physical_devices = tf.config.experimental.list_physical_devices('GPU')
+# physical_devices = tf.config.experimental.list_physical_device  
+
+tf.config.experimental.set_memory_growth(physical_devices[0], True) 
+assert tf.config.experimental.get_memory_growth(physical_devices[0]) 
+import keras
+from keras import backend as K
+# K.tensorflow_backend._get_available_gpus()
+from tensorflow.python.client import device_lib
+
+print(device_lib.list_local_devices())
+
+from keras import backend as K
+
+def mcor(y_true, y_pred):
+    #matthews_correlation
+    y_pred_pos = K.round(K.clip(y_pred, 0, 1))
+    y_pred_neg = 1 - y_pred_pos
+
+
+    y_pos = K.round(K.clip(y_true, 0, 1))
+    y_neg = 1 - y_pos
+
+
+    tp = K.sum(y_pos * y_pred_pos)
+    tn = K.sum(y_neg * y_pred_neg)
+
+
+    fp = K.sum(y_neg * y_pred_pos)
+    fn = K.sum(y_pos * y_pred_neg)
+
+
+    numerator = (tp * tn - fp * fn)
+    denominator = K.sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn))
+
+
+    return numerator / (denominator + K.epsilon())
+
+
+def precision(y_true, y_pred):
+    """Precision metric.
+
+    Only computes a batch-wise average of precision.
+
+    Computes the precision, a metric for multi-label classification of
+    how many selected items are relevant.
+    """
+    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
+    precision = true_positives / (predicted_positives + K.epsilon())
+    return precision
+
+def recall(y_true, y_pred):
+    """Recall metric.
+
+    Only computes a batch-wise average of recall.
+
+    Computes the recall, a metric for multi-label classification of
+    how many relevant items are selected.
+    """
+    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
+    recall = true_positives / (possible_positives + K.epsilon())
+    return recall
+
+
+def f1(y_true, y_pred):
+    def recall(y_true, y_pred):
+        """Recall metric.
+
+        Only computes a batch-wise average of recall.
+
+        Computes the recall, a metric for multi-label classification of
+        how many relevant items are selected.
+        """
+        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
+        recall = true_positives / (possible_positives + K.epsilon())
+        return recall
+
+    def precision(y_true, y_pred):
+        """Precision metric.
+
+        Only computes a batch-wise average of precision.
+
+        Computes the precision, a metric for multi-label classification of
+        how many selected items are relevant.
+        """
+        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
+        precision = true_positives / (predicted_positives + K.epsilon())
+        return precision
+    precision = precision(y_true, y_pred)
+    recall = recall(y_true, y_pred)
+    return 2*((precision*recall)/(precision+recall+K.epsilon()))
+
+TRAIN_SPLIT = 0.75
+TEST_SPLIT = 0.25
+INIT_LR = 1e-7
+BATCH_SIZE = 32
+NUM_EPOCHS = 10000
+image_size = 200,200
+class_mode = "binary"
+
+image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0.15,
+    width_shift_range=0.2,
+    height_shift_range=0.2,
+    shear_range=0.15,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+
+image_generatorCLASSIC = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0,
+    width_shift_range=0,
+    height_shift_range=0,
+    shear_range=0,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+
+
+
+dataDirectoryTrain = "/userdata/kerasData/preloaded/flowDirectory/train/"
+dataDirectoryValidation = "/userdata/kerasData/preloaded/flowDirectory/validation/"
+dataDirectoryTest = "/userdata/kerasData/preloaded/flowDirectory/test/"
+
+
+trainingGeneratorHPWREN = image_generator.flow_from_directory(
+    dataDirectoryTrain,
+    target_size=image_size,
+    seed=42,
+    batch_size=BATCH_SIZE,
+    class_mode=class_mode,
+    subset="training")
+
+validationGeneratorHPWREN = image_generator.flow_from_directory(
+    dataDirectoryValidation,
+    target_size=image_size,
+    batch_size=BATCH_SIZE,
+    seed=42,
+    class_mode=class_mode,
+    subset = "training")
+
+testGeneratorHPWREN = image_generatorCLASSIC.flow_from_directory(
+    dataDirectoryTest,
+    target_size=image_size,
+    batch_size=BATCH_SIZE,
+    seed=42,
+    class_mode=class_mode,
+    subset = "training")
+
+
+class FireDetectionNet:
+    @staticmethod
+    def build(width, height, depth):
+        # initialize the model along with the input shape to be
+        # "channels last" and the channels dimension itself
+        model = Sequential()
+        inputShape = (height, width, depth)
+        chanDim = -1
+        
+        model.add(SeparableConv2D(32, (7, 7), padding="same",
+                                  input_shape=inputShape))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+        
+        model.add(SeparableConv2D(64, (5,5), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+        
+        model.add(SeparableConv2D(64, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        
+        model.add(SeparableConv2D(128, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        
+
+        
+        model.add(MaxPooling2D(pool_size=(5,5)))
+        
+        model.add(Flatten())
+        model.add(Dense(64))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization())
+        model.add(Dropout(0.5))
+
+        # second set of FC => RELU layers
+        model.add(Dense(128))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization())
+        model.add(Dropout(0.5))
+
+        # softmax classifier
+        model.add(Dense(2))
+        model.add(Activation("softmax"))
+
+        # return the constructed network architecture
+        return model
+
+
+name = "HPWRENGroundUp_1024_SPLIT2_v1_e3"
+opt = SGD(lr=INIT_LR, momentum=0.9,
+    decay=INIT_LR / NUM_EPOCHS)
+groundUpModel = FireDetectionNet.build(width=200, height=200, depth=3)
+groundUpModel.compile(loss="binary_crossentropy", optimizer=opt,
+metrics=["accuracy", precision, recall, f1])
+mc = tf.keras.callbacks.ModelCheckpoint(f'/userdata/kerasData/pyimagesearch/output/experimental/{name}HPWREN.model', monitor='val_loss', mode='auto',  save_freq='epoch', verbose=1)
+early_stopping_callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=50)
+
+history = groundUpModel.fit(
+    trainingGeneratorHPWREN,
+    validation_data=validationGeneratorHPWREN,
+    steps_per_epoch=len(trainingGeneratorHPWREN) // BATCH_SIZE,
+    validation_steps= len(validationGeneratorHPWREN) // BATCH_SIZE,
+    epochs=NUM_EPOCHS,
+    callbacks=[mc, early_stopping_callback],
+    verbose=1
+)
+
+history_df = pd.DataFrame(history.history)
+hist_csv_file=f"/userdata/kerasData/output/recreate/{name}"
+with open(hist_csv_file, mode='w') as f:
+    history_df.to_csv(f)

scripts/getfiles.sh

+wget -r -A .jpg -l2 --no-parent http://hpwren.ucsd.edu/HPWREN-FIgLib/HPWREN-FIgLib-Data/  
+ls |grep -v ".*-c$"|xargs -I {} rm -rf {}
+find $PWD -maxdepth 2|grep ".*html.*"|xargs -I {} rm -rf {}

scripts/testing.ipynb

+%% Cell type:code id: tags:
+
+``` python
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import BatchNormalization
+from tensorflow.keras.layers import SeparableConv2D
+from tensorflow.keras.layers import MaxPooling2D
+from tensorflow.keras.layers import Activation
+from tensorflow.keras.layers import Flatten
+from tensorflow.keras.layers import Dropout
+from tensorflow.keras.layers import Dense
+
+import matplotlib
+matplotlib.use("Agg")
+# import the necessary packages
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.optimizers import SGD
+from tensorflow.keras.utils import to_categorical
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report
+# from imutils import paths
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import tensorflow as tf
+# from imutils import paths
+
+# import the necessary packages
+
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import cv2
+import os
+import sys
+import re
+from PIL import Image
+import pandas as pd
+import keras
+import tempfile
+from tensorflow.keras.callbacks import LambdaCallback
+physical_devices = tf.config.experimental.list_physical_devices('GPU')
+# physical_devices = tf.config.experimental.list_physical_device
+
+tf.config.experimental.set_memory_growth(physical_devices[0], True)
+assert tf.config.experimental.get_memory_growth(physical_devices[0])
+import keras
+from keras import backend as K
+# K.tensorflow_backend._get_available_gpus()
+from tensorflow.python.client import device_lib
+print(device_lib.list_local_devices())
+
+dataDirectoryTrain = "/userdata/kerasData/preloaded/flowDirectory2/train/"
+dataDirectoryValidation = "/userdata/kerasData/preloaded/flowDirectory2/validation/"
+dataDirectoryTest = "/userdata/kerasData/preloaded/flowDirectory2/test/"
+
+TRAIN_SPLIT = 0.75
+TEST_SPLIT = 0.25
+INIT_LR = 1e-2
+BATCH_SIZE = 8
+NUM_EPOCHS = 50
+image_size = 2048,1536
+class_mode = "categorical"
+
+image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0.15,
+    width_shift_range=0.2,
+    height_shift_range=0.2,
+    shear_range=0.15,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+
+image_generatorCLASSIC = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0,
+    width_shift_range=0,
+    height_shift_range=0,
+    shear_range=0,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+
+trainingGeneratorHPWREN = image_generator.flow_from_directory(
+    dataDirectoryTrain,
+    target_size=image_size,
+    seed=42,
+    batch_size=BATCH_SIZE,
+    class_mode=class_mode,
+    subset="training")
+
+validationGeneratorHPWREN = image_generator.flow_from_directory(
+    dataDirectoryValidation,
+    target_size=image_size,
+    batch_size=BATCH_SIZE,
+    seed=42,
+    class_mode=class_mode,
+    subset = "training")
+
+testGeneratorHPWREN = image_generatorCLASSIC.flow_from_directory(
+    dataDirectoryTest,
+    target_size=image_size,
+    batch_size=BATCH_SIZE,
+    seed=42,
+    class_mode=class_mode,
+    subset = "training")
+
+
+def precision(y_true, y_pred):
+    """Precision metric.
+
+    Only computes a batch-wise average of precision.
+
+    Computes the precision, a metric for multi-label classification of
+    how many selected items are relevant.
+    """
+    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
+    precision = true_positives / (predicted_positives + K.epsilon())
+    return precision
+
+def recall(y_true, y_pred):
+    """Recall metric.
+
+    Only computes a batch-wise average of recall.
+
+    Computes the recall, a metric for multi-label classification of
+    how many relevant items are selected.
+    """
+    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
+    recall = true_positives / (possible_positives + K.epsilon())
+    return recall
+
+
+def f1(y_true, y_pred):
+    def recall(y_true, y_pred):
+        """Recall metric.
+
+        Only computes a batch-wise average of recall.
+
+        Computes the recall, a metric for multi-label classification of
+        how many relevant items are selected.
+        """
+        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+        possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
+        recall = true_positives / (possible_positives + K.epsilon())
+        return recall
+
+    def precision(y_true, y_pred):
+        """Precision metric.
+
+        Only computes a batch-wise average of precision.
+
+        Computes the precision, a metric for multi-label classification of
+        how many selected items are relevant.
+        """
+        true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
+        predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
+        precision = true_positives / (predicted_positives + K.epsilon())
+        return precision
+    precision = precision(y_true, y_pred)
+    recall = recall(y_true, y_pred)
+    return 2*((precision*recall)/(precision+recall+K.epsilon()))
+```
+
+%% Output
+
+    [name: "/device:CPU:0"
+    device_type: "CPU"
+    memory_limit: 268435456
+    locality {
+    }
+    incarnation: 319115137438604482
+    , name: "/device:XLA_CPU:0"
+    device_type: "XLA_CPU"
+    memory_limit: 17179869184
+    locality {
+    }
+    incarnation: 11759642501008274543
+    physical_device_desc: "device: XLA_CPU device"
+    , name: "/device:XLA_GPU:0"
+    device_type: "XLA_GPU"
+    memory_limit: 17179869184
+    locality {
+    }
+    incarnation: 7382767696932267757
+    physical_device_desc: "device: XLA_GPU device"
+    , name: "/device:GPU:0"
+    device_type: "GPU"
+    memory_limit: 11197360384
+    locality {
+      bus_id: 1
+      links {
+      }
+    }
+    incarnation: 541433991047198862
+    physical_device_desc: "device: 0, name: Tesla K40c, pci bus id: 0000:05:00.0, compute capability: 3.5"
+    ]
+    Found 648 images belonging to 2 classes.
+    Found 243 images belonging to 2 classes.
+    Found 239 images belonging to 2 classes.
+
+%% Cell type:code id: tags:
+
+``` python
+class FireDetectionNet:
+    @staticmethod
+    def build(width, height, depth):
+        # initialize the model along with the input shape to be
+        # "channels last" and the channels dimension itself
+        model = Sequential()
+        inputShape = (height, width, depth)
+        chanDim = -1
+
+        model.add(SeparableConv2D(16, (7, 7), padding="same",
+                                  input_shape=inputShape))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+
+        model.add(SeparableConv2D(32, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+
+        model.add(SeparableConv2D(64, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(SeparableConv2D(64, (3, 3), padding="same"))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization(axis=chanDim))
+        model.add(MaxPooling2D(pool_size=(2, 2)))
+
+        model.add(Flatten())
+        model.add(Dense(128))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization())
+        model.add(Dropout(0.5))
+
+        # second set of FC => RELU layers
+        model.add(Dense(128))
+        model.add(Activation("relu"))
+        model.add(BatchNormalization())
+        model.add(Dropout(0.5))
+
+        # softmax classifier
+        model.add(Dense(2))
+        model.add(Activation("softmax"))
+
+        # return the constructed network architecture
+        return model
+
+# name = "HPWRENGroundUp_2048_V1_BATCH"
+# opt = SGD(lr=INIT_LR, momentum=0.9,
+#     decay=INIT_LR / NUM_EPOCHS)
+# groundUpModel = FireDetectionNet.build(width=2048, height=1536, depth=3)
+# groundUpModel.compile(loss="binary_crossentropy", optimizer=opt,
+# metrics=["accuracy", tf.keras.metrics.Precision(), tf.keras.metrics.Recall(), f1])
+# mc = tf.keras.callbacks.ModelCheckpoint(f'/userdata/kerasData/pyimagesearch/output/experimental/{name}HPWREN.model',
+# monitor='val_loss', mode='auto',  save_freq='epoch', verbose=1)
+# early_stopping_callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=20)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e8Modeladdress = "/userdata/kerasData/pyimagesearch/output/experimental/HPWRENGroundUp_2048_SPLIT1_v3_e6HPWREN.model"
+e7Modeladdress = "/userdata/kerasData/pyimagesearch/output/experimental/HPWRENGroundUp_2048_SPLIT1_v3_e6HPWREN.model"
+```
+
+%% Cell type:code id: tags:
+
+``` python
+testModel = FireDetectionNet.build(1536,2048,3)
+testModel.summary()
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# model = FireDetectionNet.build(width=2048, height=1536, depth=3)
+# model.load_weights(e8Modeladdress)
+attempt = tf.saved_model.load(e8Modeladdress)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e8model = tf.keras.models.load_model(e8Modeladdress,custom_objects={"f1":f1, "precision":precision, "recall":recall})
+e7model = tf.keras.models.load_model(e7Modeladdress,custom_objects={"f1":f1, "precision":precision, "recall":recall})
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e7model.
+e7model.summary()
+```
+
+%% Output
+
+    Model: "sequential"
+    _________________________________________________________________
+    Layer (type)                 Output Shape              Param #
+    =================================================================
+    separable_conv2d (SeparableC (None, 1536, 2048, 16)    211
+    _________________________________________________________________
+    activation (Activation)      (None, 1536, 2048, 16)    0
+    _________________________________________________________________
+    batch_normalization (BatchNo (None, 1536, 2048, 16)    64
+    _________________________________________________________________
+    max_pooling2d (MaxPooling2D) (None, 768, 1024, 16)     0
+    _________________________________________________________________
+    separable_conv2d_1 (Separabl (None, 768, 1024, 32)     944
+    _________________________________________________________________
+    activation_1 (Activation)    (None, 768, 1024, 32)     0
+    _________________________________________________________________
+    batch_normalization_1 (Batch (None, 768, 1024, 32)     128
+    _________________________________________________________________
+    max_pooling2d_1 (MaxPooling2 (None, 384, 512, 32)      0
+    _________________________________________________________________
+    separable_conv2d_2 (Separabl (None, 384, 512, 64)      2400
+    _________________________________________________________________
+    activation_2 (Activation)    (None, 384, 512, 64)      0
+    _________________________________________________________________
+    batch_normalization_2 (Batch (None, 384, 512, 64)      256
+    _________________________________________________________________
+    separable_conv2d_3 (Separabl (None, 384, 512, 64)      4736
+    _________________________________________________________________
+    activation_3 (Activation)    (None, 384, 512, 64)      0
+    _________________________________________________________________
+    batch_normalization_3 (Batch (None, 384, 512, 64)      256
+    _________________________________________________________________
+    max_pooling2d_2 (MaxPooling2 (None, 76, 102, 64)       0
+    _________________________________________________________________
+    flatten (Flatten)            (None, 496128)            0
+    _________________________________________________________________
+    dense (Dense)                (None, 64)                31752256
+    _________________________________________________________________
+    activation_4 (Activation)    (None, 64)                0
+    _________________________________________________________________
+    batch_normalization_4 (Batch (None, 64)                256
+    _________________________________________________________________
+    dropout (Dropout)            (None, 64)                0
+    _________________________________________________________________
+    dense_1 (Dense)              (None, 128)               8320
+    _________________________________________________________________
+    activation_5 (Activation)    (None, 128)               0
+    _________________________________________________________________
+    batch_normalization_5 (Batch (None, 128)               512
+    _________________________________________________________________
+    dropout_1 (Dropout)          (None, 128)               0
+    _________________________________________________________________
+    dense_2 (Dense)              (None, 2)                 258
+    _________________________________________________________________
+    activation_6 (Activation)    (None, 2)                 0
+    =================================================================
+    Total params: 31,770,597
+    Trainable params: 31,769,861
+    Non-trainable params: 736
+    _________________________________________________________________
+
+%% Cell type:code id: tags:
+
+``` python
+e8model.summary()
+```
+
+%% Output
+
+    Model: "sequential"
+    _________________________________________________________________
+    Layer (type)                 Output Shape              Param #
+    =================================================================
+    separable_conv2d (SeparableC (None, 1536, 2048, 16)    211
+    _________________________________________________________________
+    activation (Activation)      (None, 1536, 2048, 16)    0
+    _________________________________________________________________
+    batch_normalization (BatchNo (None, 1536, 2048, 16)    64
+    _________________________________________________________________
+    max_pooling2d (MaxPooling2D) (None, 768, 1024, 16)     0
+    _________________________________________________________________
+    separable_conv2d_1 (Separabl (None, 768, 1024, 32)     944
+    _________________________________________________________________
+    activation_1 (Activation)    (None, 768, 1024, 32)     0
+    _________________________________________________________________
+    batch_normalization_1 (Batch (None, 768, 1024, 32)     128
+    _________________________________________________________________
+    max_pooling2d_1 (MaxPooling2 (None, 384, 512, 32)      0
+    _________________________________________________________________
+    separable_conv2d_2 (Separabl (None, 384, 512, 64)      2400
+    _________________________________________________________________
+    activation_2 (Activation)    (None, 384, 512, 64)      0
+    _________________________________________________________________
+    batch_normalization_2 (Batch (None, 384, 512, 64)      256
+    _________________________________________________________________
+    separable_conv2d_3 (Separabl (None, 384, 512, 64)      4736
+    _________________________________________________________________
+    activation_3 (Activation)    (None, 384, 512, 64)      0
+    _________________________________________________________________
+    batch_normalization_3 (Batch (None, 384, 512, 64)      256
+    _________________________________________________________________
+    max_pooling2d_2 (MaxPooling2 (None, 76, 102, 64)       0
+    _________________________________________________________________
+    flatten (Flatten)            (None, 496128)            0
+    _________________________________________________________________
+    dense (Dense)                (None, 64)                31752256
+    _________________________________________________________________
+    activation_4 (Activation)    (None, 64)                0
+    _________________________________________________________________
+    batch_normalization_4 (Batch (None, 64)                256
+    _________________________________________________________________
+    dropout (Dropout)            (None, 64)                0
+    _________________________________________________________________
+    dense_1 (Dense)              (None, 128)               8320
+    _________________________________________________________________
+    activation_5 (Activation)    (None, 128)               0
+    _________________________________________________________________
+    batch_normalization_5 (Batch (None, 128)               512
+    _________________________________________________________________
+    dropout_1 (Dropout)          (None, 128)               0
+    _________________________________________________________________
+    dense_2 (Dense)              (None, 2)                 258
+    _________________________________________________________________
+    activation_6 (Activation)    (None, 2)                 0
+    =================================================================
+    Total params: 31,770,597
+    Trainable params: 31,769,861
+    Non-trainable params: 736
+    _________________________________________________________________
+
+%% Cell type:code id: tags:
+
+``` python
+e1048model = tf.keras.models.load_model("/userdata/kerasData/pyimagesearch/output/experimental/HPWRENGroundUp_1024_SPLIT1_v1_e3HPWREN.model",custom_objects={"f1":f1, "precision":precision, "recall":recall})
+e1048model.summary()
+```
+
+%% Output
+
+    Model: "sequential"
+    _________________________________________________________________
+    Layer (type)                 Output Shape              Param #
+    =================================================================
+    separable_conv2d (SeparableC (None, 768, 1024, 32)     275
+    _________________________________________________________________
+    activation (Activation)      (None, 768, 1024, 32)     0
+    _________________________________________________________________
+    batch_normalization (BatchNo (None, 768, 1024, 32)     128
+    _________________________________________________________________
+    max_pooling2d (MaxPooling2D) (None, 384, 512, 32)      0
+    _________________________________________________________________
+    separable_conv2d_1 (Separabl (None, 384, 512, 64)      2912
+    _________________________________________________________________
+    activation_1 (Activation)    (None, 384, 512, 64)      0
+    _________________________________________________________________
+    batch_normalization_1 (Batch (None, 384, 512, 64)      256
+    _________________________________________________________________
+    max_pooling2d_1 (MaxPooling2 (None, 192, 256, 64)      0
+    _________________________________________________________________
+    separable_conv2d_2 (Separabl (None, 192, 256, 64)      4736
+    _________________________________________________________________
+    activation_2 (Activation)    (None, 192, 256, 64)      0
+    _________________________________________________________________
+    batch_normalization_2 (Batch (None, 192, 256, 64)      256
+    _________________________________________________________________
+    separable_conv2d_3 (Separabl (None, 192, 256, 128)     8896
+    _________________________________________________________________
+    activation_3 (Activation)    (None, 192, 256, 128)     0
+    _________________________________________________________________
+    batch_normalization_3 (Batch (None, 192, 256, 128)     512
+    _________________________________________________________________
+    separable_conv2d_4 (Separabl (None, 192, 256, 256)     34176
+    _________________________________________________________________
+    activation_4 (Activation)    (None, 192, 256, 256)     0
+    _________________________________________________________________
+    batch_normalization_4 (Batch (None, 192, 256, 256)     1024
+    _________________________________________________________________
+    max_pooling2d_2 (MaxPooling2 (None, 38, 51, 256)       0
+    _________________________________________________________________
+    flatten (Flatten)            (None, 496128)            0
+    _________________________________________________________________
+    dense (Dense)                (None, 64)                31752256
+    _________________________________________________________________
+    activation_5 (Activation)    (None, 64)                0
+    _________________________________________________________________
+    batch_normalization_5 (Batch (None, 64)                256
+    _________________________________________________________________
+    dropout (Dropout)            (None, 64)                0
+    _________________________________________________________________
+    dense_1 (Dense)              (None, 128)               8320
+    _________________________________________________________________
+    activation_6 (Activation)    (None, 128)               0
+    _________________________________________________________________
+    batch_normalization_6 (Batch (None, 128)               512
+    _________________________________________________________________
+    dropout_1 (Dropout)          (None, 128)               0
+    _________________________________________________________________
+    dense_2 (Dense)              (None, 2)                 258
+    _________________________________________________________________
+    activation_7 (Activation)    (None, 2)                 0
+    =================================================================
+    Total params: 31,814,773
+    Trainable params: 31,813,301
+    Non-trainable params: 1,472
+    _________________________________________________________________
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e8model.evaluate(testGeneratorHPWREN)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e7model.evaluate(testGeneratorHPWREN)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e6model.evaluate(testGeneratorHPWREN)
+```
+
+%% Output
+
+    30/30 [==============================] - 242s 8s/step - loss: 0.8597 - accuracy: 0.4728 - precision: 0.4728 - recall: 0.4728 - f1: 0.4720
+
+    [0.8597329258918762,
+     0.47280335426330566,
+     0.47280335426330566,
+     0.47280335426330566,
+     0.47202378511428833]
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+%matplotlib inline
+lrs = LRfINDER.lrs[10:-1]
+losses = LRfINDER.losses[10:-1]
+plt.plot(lrs, losses)
+plt.xscale("log")
+plt.xlabel("Learning Rate (Log Scale)")
+plt.ylabel("Loss")
+```
+
+%% Output
+
+    Text(0, 0.5, 'Loss')
+
+
+
+%% Cell type:code id: tags:
+
+``` python
+image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=30,
+    zoom_range=0.15,
+    width_shift_range=0.2,
+    height_shift_range=0.2,
+    shear_range=0.15,
+    validation_split=0,
+    horizontal_flip=True,
+    fill_mode="nearest")
+```
+
+%% Cell type:code id: tags:
+
+``` python
+testImage = image_generator.flow_from_("/userdata/kerasData/preloaded/flowDirectory2/test/fire/1512676696_+02100.jpg")))
+```
+
+%% Cell type:code id: tags:
+
+``` python
+testImage.shape
+```
+
+%% Output
+
+    (1536, 2048, 3)
+
+%% Cell type:code id: tags:
+
+``` python
+```
+
+%% Cell type:code id: tags:
+
+``` python
+e6model.predict(testImage)
+```
+
+%% Output
+
+    ---------------------------------------------------------------------------
+    ValueError                                Traceback (most recent call last)
+    <ipython-input-48-d3b35444c1d2> in <module>
+    ----> 1 e6model.predict(testImage)
+
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
+         86       raise ValueError('{} is not supported in multi-worker mode.'.format(
+         87           method.__name__))
+    ---> 88     return method(self, *args, **kwargs)
+         89
+         90   return tf_decorator.make_decorator(
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
+       1266           for step in data_handler.steps():
+       1267             callbacks.on_predict_batch_begin(step)
+    -> 1268             tmp_batch_outputs = predict_function(iterator)
+       1269             # Catch OutOfRangeError for Datasets of unknown size.
+       1270             # This blocks until the batch has finished executing.
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
+        578         xla_context.Exit()
+        579     else:
+    --> 580       result = self._call(*args, **kwds)
+        581
+        582     if tracing_count == self._get_tracing_count():
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
+        625       # This is the first call of __call__, so we have to initialize.
+        626       initializers = []
+    --> 627       self._initialize(args, kwds, add_initializers_to=initializers)
+        628     finally:
+        629       # At this point we know that the initialization is complete (or less
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
+        504     self._concrete_stateful_fn = (
+        505         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
+    --> 506             *args, **kwds))
+        507
+        508     def invalid_creator_scope(*unused_args, **unused_kwds):
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
+       2444       args, kwargs = None, None
+       2445     with self._lock:
+    -> 2446       graph_function, _, _ = self._maybe_define_function(args, kwargs)
+       2447     return graph_function
+       2448
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
+       2775
+       2776       self._function_cache.missed.add(call_context_key)
+    -> 2777       graph_function = self._create_graph_function(args, kwargs)
+       2778       self._function_cache.primary[cache_key] = graph_function
+       2779       return graph_function, args, kwargs
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
+       2665             arg_names=arg_names,
+       2666             override_flat_arg_shapes=override_flat_arg_shapes,
+    -> 2667             capture_by_value=self._capture_by_value),
+       2668         self._function_attributes,
+       2669         # Tell the ConcreteFunction to clean up its graph once it goes out of
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
+        979         _, original_func = tf_decorator.unwrap(python_func)
+        980
+    --> 981       func_outputs = python_func(*func_args, **func_kwargs)
+        982
+        983       # invariant: `func_outputs` contains only Tensors, CompositeTensors,
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
+        439         # __wrapped__ allows AutoGraph to swap in a converted function. We give
+        440         # the function a weak reference to itself to avoid a reference cycle.
+    --> 441         return weak_wrapped_fn().__wrapped__(*args, **kwds)
+        442     weak_wrapped_fn = weakref.ref(wrapped_fn)
+        443
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
+        966           except Exception as e:  # pylint:disable=broad-except
+        967             if hasattr(e, "ag_error_metadata"):
+    --> 968               raise e.ag_error_metadata.to_exception(e)
+        969             else:
+        970               raise
+    ValueError: in user code:
+
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:1147 predict_function  *
+        outputs = self.distribute_strategy.run(
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
+        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
+        return self._call_for_each_replica(fn, args, kwargs)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
+        return fn(*args, **kwargs)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:1122 predict_step  **
+        return self(x, training=False)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py:886 __call__
+        self.name)
+    /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/input_spec.py:180 assert_input_compatibility
+        str(x.shape.as_list()))
+
+    ValueError: Input 0 of layer sequential is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [32, 2048, 3]