Updated requirements

The release of TF2.0 and Numpy 1.17 causes a number of "future warning" error messages. Specifically setting things to include Keras and Numpy 1.16.4 removes these errors without needing to update the entire code base.

.gitignore

@@ -118,3 +118,4 @@ results.html
 !requirements-gpu.txt
 !tests/models/*
 !tests/data/*
+!docs/*

README.md

@@ -3,8 +3,21 @@ Give those screenshots of yours a quick eyeballing.
 
 Eyeballer is meant for large-scope network penetration tests where you need to find "interesting" targets from a huge set of web-based hosts. Go ahead and use your favorite screenshotting tool like normal (EyeWitness or GoWitness) and then run them through Eyeballer to tell you what's likely to contain vulnerabilities, and what isn't.
 
+
+### Example Labels
+
+| Old-Looking Sites | Login Pages |
+| ------ |:-----:|
+| ![Sample Old-looking Page](/docs/old-looking.png) | ![Sample Login Page](/docs/login.png) |
+
+| Homepages | Custom 404's |
+| ------ |:-----:|
+| ![Sample Homepage](/docs/homepage.png) | ![Sample Custom 404](/docs/404.png) |
+
 ## Setup
 
+Eyeballer uses TF.keras on Tensorflow 2.0. This is (as of this moment) still in "beta". So the pip requirement for it looks a bit weird. It'll also probably conflict with an existing TensorFlow installation if you've got the regular 1.0 version installed. So, heads-up there. But 2.0 should be out of beta and official "soon" according to Google, so this problem ought to solve itself in short order.
+
 Download required packages on pip:
 ```
 sudo pip3 install -r requirements.txt
@@ -15,6 +28,20 @@ Or if you want GPU support:
 sudo pip3 install -r requirements-gpu.txt
 ```
 
+**NOTE**: Setting up a GPU for use with TensorFlow is way beyond the scope of this README. There's hardware compatibility to consider, drivers to install... There's a lot. So you're just going to have to figure this part out on your own if you want a GPU. But at least from a Python package perspective, the above requirements file has you covered.
+
+**Training Data** You can find our training data here:
+
+https://www.dropbox.com/sh/7aouywaid7xptpq/AAD_-I4hAHrDeiosDAQksnBma?dl=1
+
+Pretty soon, we're going to add this as a TensorFlow DataSet, so you don't need to download this separately like this. It'll also let us version the data a bit better. But for now, just deal with it. There's two things you need from the training data:
+
+1. `images/` folder, containing all the screenshots (resized down to 224x140. We'll have the full-size images up soon)
+2. `labels.csv` that has all the labels
+3. `bishop-fox-pretrained-v1.h5` A pretrained weights file you can use right out of the box without training.
+
+Copy all three into the root of the Eyeballer code tree.
+
 ## Predicting Labels
 To eyeball some screenshots, just run the "predict" mode:
 
@@ -28,6 +55,9 @@ Or for a whole directory of files:
 eyeballer.py --weights YOUR_WEIGHTS.h5 predict PATH_TO/YOUR_FILES/
 ```
 
+Eyeballer will spit the results back to you in human readable format (a `results.html` file so you can browse it easily) and machine readable format (a `results.csv` file).
+
+
 ## Training
 To train a new model, run:
 ```
@@ -45,3 +75,5 @@ You just trained a new model, cool! Let's see how well it performs against some
 ```
 eyeballer.py --weights YOUR_WEIGHTS.h5 evaluate
 ```
+
+The output will describe the model's accuracy in both recall and precision for each of the program's labels. (Including "none of the above" as a pseudo-label)

eyeballer/augmentation.py

@@ -1,7 +1,7 @@
 import numpy as np
 
 from Augmentor.Operations import Operation
-from keras.applications.mobilenet import preprocess_input
+from tensorflow.keras.applications.mobilenet import preprocess_input
 
 
 class EyeballerAugmentation(Operation):

eyeballer/model.py

@@ -31,7 +31,7 @@ class EyeballModel:
     image_width, image_height = 224, 224
     input_shape = (image_width, image_height, 3)
 
-    def __init__(self, weights_file, print_summary=False, seed=None):
+    def __init__(self, weights_file, print_summary=False, seed=None, quiet=False):
         """Constructor for model class.
 
         Keyword arguments:
@@ -60,6 +60,8 @@ class EyeballModel:
         if print_summary:
             print(self.model.summary())
 
+        self.quiet = quiet
+
         # Pull out our labels for use in generators later
         data = pd.read_csv("labels.csv")
         self.training_labels = data.loc[data['evaluation'] == False]  # noqa: E712
@@ -216,7 +218,10 @@ class EyeballModel:
             raise FileNotFoundError
 
         results = []
-        for screenshot in progressbar.progressbar(screenshots):
+        bar = progressbar.ProgressBar()
+        if self.quiet:
+            bar = progressbar.NullBar()
+        for screenshot in bar(screenshots):
             # Load the image into memory
             img = None
             try:

eyeballer/visualization.py

@@ -1,6 +1,7 @@
 import numpy as np
 import math
-from keras.preprocessing import image
+import tensorflow as tf
+
 from copy import deepcopy
 from matplotlib import pyplot as plt
 from eyeballer.model import DATA_LABELS
@@ -10,8 +11,8 @@ class HeatMap():
     def __init__(self, screenshot_path, model, threshold=0.5, boxsize=28, step=7):
         self.model = model
 
-        img = image.load_img(screenshot_path, target_size=(self.model.image_width, self.model.image_height))
-        img = image.img_to_array(img)
+        img = tf.keras.preprocessing.image.load_img(screenshot_path, target_size=(self.model.image_width, self.model.image_height))
+        img = tf.keras.preprocessing.image.img_to_array(img)
 
         self.screenshot = img
         self.boxsize = boxsize
@@ -43,7 +44,7 @@ class HeatMap():
                         labels.append(label)
 
         plt.figure()
-        screenshot_image = image.load_img(self.screenshot_path, target_size=(self.model.image_width, self.model.image_width))
+        screenshot_image = tf.keras.preprocessing.image.load_img(self.screenshot_path, target_size=(self.model.image_width, self.model.image_width))
         _, subplots = plt.subplots(1, len(heatmaps))
         # This is a little janky, but matplotlib returns a list above if there's multiple subplots, and just a single subplot if there's only one
         #   it would have been easier if it was always a list. But alas

requirements.txt

@@ -1,7 +1,8 @@
 Augmentor
 click
 matplotlib
-numpy
+numpy==1.16.4
+keras
 pandas
 pillow
 sklearn

tests/EvaluateTest.py

@@ -1 +0,0 @@
-#TODO

tests/PredictTest.py

@@ -25,7 +25,8 @@ class PredictTest(unittest.TestCase):
         model_kwargs = {
             "weights_file": weights_file,
             "print_summary": False,
-            "seed": None
+            "seed": None,
+            "quiet": True
         }
         self.model = EyeballModel(**model_kwargs)
 
@@ -33,7 +34,8 @@ class PredictTest(unittest.TestCase):
         model_kwargs = {
             "weights_file": None,
             "print_summary": False,
-            "seed": 12345678
+            "seed": 12345678,
+            "quiet": True
         }
         same_seed_model = EyeballModel(**model_kwargs)
 
@@ -48,7 +50,8 @@ class PredictTest(unittest.TestCase):
         model_kwargs = {
             "weights_file": None,
             "print_summary": False,
-            "seed": 12345678
+            "seed": 12345678,
+            "quiet": True
         }
         same_seed_model = EyeballModel(**model_kwargs)
 

tests/TrainTest.py

@@ -1 +0,0 @@
-#TODO