add all the files

.gitignore

@@ -0,0 +1,69 @@
+# Data files and directories common in repo root
+datasets/
+logs/
+*.h5
+results/
+temp/
+test/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# VS Studio Code
+.vscode
+
+# PyCharm
+.idea/
+
+# Dropbox
+.dropbox.attr
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# 
+dlib_front_and_rear_vehicles_v1/
+lisa/
+*.jpg
+*.png
+*.hdf5
+*.model
+*.pickle
+*.tar
+*.csv

Imagenet-Bundle/age_gender/build_dataset.py

@@ -0,0 +1,93 @@
+# import the necessary packages
+from config import age_gender_config as config
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+from pyimagesearch.utils import AgeGenderHelper
+import numpy as np
+import progressbar
+import pickle
+import json
+
+import cv2
+# initialize our helper class, then build the set of image paths
+# and class labels
+print("[INFO] building paths and labels...")
+agh = AgeGenderHelper(config)
+(trainPaths, trainLabels) = agh.buildPathsAndLabels()
+# now that we have the total number of images in the dataset that
+# can be used for training, compute the number of images that
+# should be used for validation and testing
+numVal = int(len(trainPaths) * config.NUM_VAL_IMAGES)
+numTest = int(len(trainPaths) * config.NUM_TEST_IMAGES)
+# our class labels are represented as strings so we need to encode
+# them
+print("[INFO] encoding labels...")
+le = LabelEncoder().fit(trainLabels)
+trainLabels = le.transform(trainLabels)
+
+# perform sampling from the training set to construct a a validation
+# set
+print("[INFO] constructing validation data...")
+split = train_test_split(trainPaths, trainLabels, test_size=numVal,
+stratify=trainLabels)
+(trainPaths, valPaths, trainLabels, valLabels) = split
+
+# perform stratified sampling from the training set to construct a
+# a testing set
+print("[INFO] constructing testing data...")
+split = train_test_split(trainPaths, trainLabels, test_size=numTest,
+stratify=trainLabels)
+(trainPaths, testPaths, trainLabels, testLabels) = split
+
+# construct a list pairing the training, validation, and testing
+# image paths along with their corresponding labels and output list
+# files
+datasets = [
+("train", trainPaths, trainLabels, config.TRAIN_MX_LIST),
+("val", valPaths, valLabels, config.VAL_MX_LIST),
+("test", testPaths, testLabels, config.TEST_MX_LIST)]
+# initialize the lists of RGB channel averages
+(R, G, B) = ([], [], [])
+
+# loop over the dataset tuples
+for (dType, paths, labels, outputPath) in datasets:
+# open the output file for writing
+print("[INFO] building {}...".format(outputPath))
+f = open(outputPath, "w")
+# initialize the progress bar
+widgets = ["Building List: ", progressbar.Percentage(), " ",
+progressbar.Bar(), " ", progressbar.ETA()]
+pbar = progressbar.ProgressBar(maxval=len(paths),
+widgets=widgets).start()
+
+# loop over each of the individual images + labels
+for (i, (path, label)) in enumerate(zip(paths, labels)):
+# if we are building the training dataset, then compute the
+# mean of each channel in the image, then update the
+# respective lists
+if dType == "train":
+image = cv2.imread(path)
+(b, g, r) = cv2.mean(image)[:3]
+R.append(r)
+G.append(g)
+B.append(b)
+# write the image index, label, and output path to file
+row = "\t".join([str(i), str(label), path])
+f.write("{}\n".format(row))
+pbar.update(i)
+# close the output file
+pbar.finish()
+f.close()
+
+# construct a dictionary of averages, then serialize the means to a
+# JSON file
+print("[INFO] serializing means...")
+D = {"R": np.mean(R), "G": np.mean(G), "B": np.mean(B)}
+f = open(config.DATASET_MEAN, "w")
+f.write(json.dumps(D))
+f.close()
+# serialize the label encoder
+print("[INFO] serializing label encoder...")
+f = open(config.LABEL_ENCODER_PATH, "wb")
+f.write(pickle.dumps(le))
+f.close()

Imagenet-Bundle/age_gender/config/age_gender_config.py

@@ -0,0 +1,68 @@
+# import the necessary packages
+from os import path
+# define the type of dataset we are training (i.e., either "age" or
+# "gender")
+DATASET_TYPE = "gender"
+# define the base paths to the faces dataset and output path
+BASE_PATH = "/raid/datasets/adience"
+OUTPUT_BASE = "output"
+MX_OUTPUT = BASE_PATH
+# based on the base path, derive the images path and folds path
+IMAGES_PATH = path.sep.join([BASE_PATH, "aligned"])
+LABELS_PATH = path.sep.join([BASE_PATH, "folds"])
+
+# define the percentage of validation and testing images relative
+# to the number of training images
+NUM_VAL_IMAGES = 0.15
+NUM_TEST_IMAGES = 0.15
+
+# define the batch size
+BATCH_SIZE = 128
+NUM_DEVICES = 2
+
+# check to see if we are working with the "age" portion of the
+# dataset
+if DATASET_TYPE == "age":
+    # define the number of labels for the "age" dataset, along with
+    # the path to the label encoder
+    NUM_CLASSES = 8
+    LABEL_ENCODER_PATH = path.sep.join([OUTPUT_BASE,
+                                        "age_le.cpickle"])
+    # define the path to the output training, validation, and testing
+    # lists
+    TRAIN_MX_LIST = path.sep.join([MX_OUTPUT, "lists/age_train.lst"])
+    VAL_MX_LIST = path.sep.join([MX_OUTPUT, "lists/age_val.lst"])
+    TEST_MX_LIST = path.sep.join([MX_OUTPUT, "lists/age_test.lst"])
+    # define the path to the output training, validation, and testing
+    # image records
+    TRAIN_MX_REC = path.sep.join([MX_OUTPUT, "rec/age_train.rec"])
+    VAL_MX_REC = path.sep.join([MX_OUTPUT, "rec/age_val.rec"])
+    TEST_MX_REC = path.sep.join([MX_OUTPUT, "rec/age_test.rec"])
+    # derive the path to the mean pixel file
+    DATASET_MEAN = path.sep.join([OUTPUT_BASE,
+                                  "age_adience_mean.json"])
+
+# otherwise, check to see if we are performing "gender"
+# classification
+elif DATASET_TYPE == "gender":
+    # define the number of labels for the "gender" dataset, along
+    # with the path to the label encoder
+    NUM_CLASSES = 2
+    LABEL_ENCODER_PATH = path.sep.join([OUTPUT_BASE,
+                                        "gender_le.cpickle"])
+    # define the path to the output training, validation, and testing
+    # lists
+    TRAIN_MX_LIST = path.sep.join([MX_OUTPUT,
+                                   "lists/gender_train.lst"])
+    VAL_MX_LIST = path.sep.join([MX_OUTPUT,
+                                 "lists/gender_val.lst"])
+    TEST_MX_LIST = path.sep.join([MX_OUTPUT,
+                                  "lists/gender_test.lst"])
+    # define the path to the output training, validation, and testing
+    # image records
+    TRAIN_MX_REC = path.sep.join([MX_OUTPUT, "rec/gender_train.rec"])
+    VAL_MX_REC = path.sep.join([MX_OUTPUT, "rec/gender_val.rec"])
+    TEST_MX_REC = path.sep.join([MX_OUTPUT, "rec/gender_test.rec"])
+    # derive the path to the mean pixel file
+    DATASET_MEAN = path.sep.join([OUTPUT_BASE,
+                                  "gender_adience_mean.json"])

Imagenet-Bundle/car_classification/build_dataset.py

@@ -0,0 +1,83 @@
+# import the necessary packages
+from config import car_config as config
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+import progressbar
+import pickle
+import os
+# read the contents of the labels file, then initialize the list of
+# image paths and labels
+print("[INFO] loading image paths and labels...")
+rows = open(config.LABELS_PATH).read()
+rows = rows.strip().split("\n")[1:]
+trainPaths = []
+trainLabels = []
+
+# loop over the rows
+for row in rows:
+    # unpack the row, then update the image paths and labels list
+    # (filename, make) = row.split(",")[:2]
+    (filename, make, model) = row.split(",")[:3]
+    filename = filename[filename.rfind("/") + 1:]
+    trainPaths.append(os.sep.join([config.IMAGES_PATH, filename]))
+    trainLabels.append("{}:{}".format(make, model))
+
+# now that we have the total number of images in the dataset that
+# can be used for training, compute the number of images that
+# should be used for validation and testing
+numVal = int(len(trainPaths) * config.NUM_VAL_IMAGES)
+numTest = int(len(trainPaths) * config.NUM_TEST_IMAGES)
+
+# our class labels are represented as strings so we need to encode
+# them
+print("[INFO] encoding labels...")
+le = LabelEncoder().fit(trainLabels)
+trainLabels = le.transform(trainLabels)
+
+# perform sampling from the training set to construct a a validation
+# set
+print("[INFO] constructing validation data...")
+split = train_test_split(trainPaths, trainLabels, test_size=numVal,
+                         stratify=trainLabels)
+(trainPaths, valPaths, trainLabels, valLabels) = split
+# perform stratified sampling from the training set to construct a
+# a testing set
+print("[INFO] constructing testing data...")
+split = train_test_split(trainPaths, trainLabels, test_size=numTest,
+                         stratify=trainLabels)
+(trainPaths, testPaths, trainLabels, testLabels) = split
+
+# construct a list pairing the training, validation, and testing
+# image paths along with their corresponding labels and output list
+# files
+datasets = [
+("train", trainPaths, trainLabels, config.TRAIN_MX_LIST),
+("val", valPaths, valLabels, config.VAL_MX_LIST),
+("test", testPaths, testLabels, config.TEST_MX_LIST)]
+
+# loop over the dataset tuples
+for (dType, paths, labels, outputPath) in datasets:
+    # open the output file for writing
+    print("[INFO] building {}...".format(outputPath))
+    f = open(outputPath, "w")
+    # initialize the progress bar
+    widgets = ["Building List: ", progressbar.Percentage(), " ",
+               progressbar.Bar(), " ", progressbar.ETA()]
+    pbar = progressbar.ProgressBar(maxval=len(paths),
+                                   widgets=widgets).start()
+
+    # loop over each of the individual images + labels
+    for (i, (path, label)) in enumerate(zip(paths, labels)):
+        # write the image index, label, and output path to file
+        row = "\t".join([str(i), str(label), path])
+        f.write("{}\n".format(row))
+        pbar.update(i)
+    # close the output file
+    pbar.finish()
+    f.close()
+
+# write the label encoder to file
+print("[INFO] serializing label encoder...")
+f = open(config.LABEL_ENCODER_PATH, "wb")
+f.write(pickle.dumps(le))
+f.close()

Imagenet-Bundle/car_classification/config/car_config.py

@@ -0,0 +1,38 @@
+# import the necessary packages
+from os import path
+# define the base path to the cars dataset
+BASE_PATH = "/raid/datasets/cars"
+# based on the base path, derive the images path and meta file path
+IMAGES_PATH = path.sep.join([BASE_PATH, "car_ims"])
+LABELS_PATH = path.sep.join([BASE_PATH, "complete_dataset.csv"])
+
+# define the path to the output training, validation, and testing
+# lists
+MX_OUTPUT = BASE_PATH
+TRAIN_MX_LIST = path.sep.join([MX_OUTPUT, "lists/train.lst"])
+VAL_MX_LIST = path.sep.join([MX_OUTPUT, "lists/val.lst"])
+TEST_MX_LIST = path.sep.join([MX_OUTPUT, "lists/test.lst"])
+
+# define the path to the output training, validation, and testing
+# image records
+TRAIN_MX_REC = path.sep.join([MX_OUTPUT, "rec/train.rec"])
+VAL_MX_REC = path.sep.join([MX_OUTPUT, "rec/val.rec"])
+TEST_MX_REC = path.sep.join([MX_OUTPUT, "rec/test.rec"])
+
+# define the path to the label encoder
+LABEL_ENCODER_PATH = path.sep.join([BASE_PATH, "output/le.cpickle"])
+
+# define the RGB means from the ImageNet dataset
+R_MEAN = 123.68
+G_MEAN = 116.779
+B_MEAN = 103.939
+
+# define the percentage of validation and testing images relative
+# to the number of training images
+NUM_CLASSES = 164
+NUM_VAL_IMAGES = 0.15
+NUM_TEST_IMAGES = 0.15
+
+# define the batch size
+BATCH_SIZE = 32
+NUM_DEVICES = 1