WIP

.gitignore

@@ -0,0 +1,6 @@
+.idea/*
+.vscode/*
+logs/*
+data/*
+.data/*
+_pycache_\*

Dockerfile

@@ -1,4 +1,5 @@
 FROM nvidia/cuda:8.0-cudnn6-devel
+MAINTAINER snehil.wakchaure1@cerner.com
 
 ENV LANG=C.UTF-8 LC_ALL=C.UTF-8
 
@@ -36,6 +37,7 @@ RUN conda install -y python=${python_version} && \
     pip install opencv-contrib-python && \
     conda install -y Pillow scikit-learn scikit-image graphviz pydot notebook pandas matplotlib mkl nose pyyaml six h5py && \
     pip install keras && \
+    pip install tensorflow && \
     conda clean -yt
 
 ENV PYTHONPATH='/src/:$PYTHONPATH'

README.md

@@ -1,8 +1,6 @@
-# Abnormal Event Detection in Videos Using Spatiotemporal Autoencoder
+# Anomaly detection in Smart Audio Videos using a Convolutional Spatio-temporal Auto-encoder and Convolutional Long-Short Term Memory (LSTM) Recurrent Neural Network based architecture.
-This repository hosts the codes for "Abnormal Event Detection in Videos Using Spatiotemporal Autoencoder".
-Paper can be found at [Springer](https://link.springer.com/chapter/10.1007/978-3-319-59081-3_23) and [arXiv](https://arxiv.org/abs/1701.01546).
 
-Prerequisites:
+## Project dependencies:
 - keras
 - tensorflow
 - h5py
@@ -12,32 +10,37 @@ Prerequisites:
 - tqdm (for progressbar)
 - coloredlogs (optional, for colored terminal logs only)
 
-You can use the `Dockerfile` provided to build the environment then enter the environment using `nvidia-docker run --rm -it -v HOST_FOLDER:/share DOCKER_IMAGE bash`.
+To build the docker image run the following docker command. This will take around 13GB space on your machine so makes sure you clean up any unused docker images and containers to avoid out of free space issues.
+```docker build -t snehil/video_anomaly_ai:v1 .```
 
-To train the model, just run `python start_train.py`. Default configuration can be found at `config.yml`. You need to prepare video dataset you plan to train/evaluate on. You may get the benchmark dataset videos from respective authors. For each dataset, put the training videos into `VIDEO_ROOT_PATH/DATASET_NAME/training_videos` and testing videos into `VIDEO_ROOT_PATH/DATASET_NAME/testing_videos`. Example structure of training videos for `avenue` dataset:
+You can then enter the environment using ```nvidia-docker run --rm -it -v HOST_FOLDER:/share DOCKER_IMAGE bash```.
+
+or run the following command:
+```docker run --rm -it -v ~/:/share snehil/<IMAGE_ID> bash```
+
+To login to a running container:
+```docker attach <CONTAINER_ID>```
+
+## To train the model 
+
+ - Just run `python start_train.py`. 
+ - Default configuration can be found at `config.yml`. 
+ - You need to prepare video dataset you plan to train/evaluate on (avi or mp4). For each dataset, put the training videos into ```   
+   ./data/videos/training_videos``` and testing videos into ```./data/videos/testing_videos```. Example structure of training videos for `avenue` dataset:
  - `VIDEO_ROOT_PATH/avenue/training_videos`
   - `01.avi`
   - `02.avi`
   - ...
   - `16.avi`
 
+## To test the model
 Once you have trained the model, you may now run `python start_test.py` after setting the parameters at the beginning of the file.
 
-Please cite the following paper if you use our code / paper:
+# Troubleshooting
+
+In case you get a No free space left error (inspite of having free space) while running the docker build command, try cleaning up unused docker images and containers using the following commands
 ```
-@inbook{Chong2017,
+docker rm $(docker ps -q -f 'status=exited')
-  author    = {Chong, Yong Shean and
+docker rmi $(docker images -q -f "dangling=true")
-               Tay, Yong Haur},
+
-  editor    = {Cong, Fengyu and
-               Leung, Andrew and
-               Wei, Qinglai},
-  title     = {Abnormal Event Detection in Videos Using Spatiotemporal Autoencoder},
-  bookTitle = {Advances in Neural Networks - ISNN 2017: 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21--26, 2017, Proceedings, Part II},
-  year      = {2017},
-  publisher = {Springer International Publishing},
-  pages     = {189--196},
-  isbn      = {978-3-319-59081-3},
-  doi       = {10.1007/978-3-319-59081-3_23},
-  url       = {https://doi.org/10.1007/978-3-319-59081-3_23}
-}
 ```

classifier.py

@@ -1,7 +1,7 @@
-from dataset import preprocess_data
 import os
-from keras import backend as K
 import matplotlib
+from   keras      import backend as K
+from   dataset    import preprocess_data
 matplotlib.use('Agg')
 
 assert(K.image_data_format() == 'channels_last')
@@ -18,19 +18,41 @@ def get_model(t):
 
     input_tensor = Input(shape=(t, 224, 224, 1))
 
-    conv1 = TimeDistributed(Conv2D(128, kernel_size=(11, 11), padding='same', strides=(4, 4), name='conv1'),
+    # First Conv layer
-                            input_shape=(t, 224, 224, 1))(input_tensor)
+    conv1        = TimeDistributed(
+                        Conv2D(
+                            128, 
+                            kernel_size = (11, 11), 
+                            padding     = 'same',  # zero-padding
+                            strides     = (4, 4), 
+                            name        = 'conv1'
+                        ),
+                        input_shape=(t, 224, 224, 1)
+                    )(input_tensor)
+
     conv1        = TimeDistributed(BatchNormalization())(conv1)
     conv1        = TimeDistributed(Activation('relu'))(conv1)
 
-    conv2 = TimeDistributed(Conv2D(64, kernel_size=(5, 5), padding='same', strides=(2, 2), name='conv2'))(conv1)
+    # Second Conv layer
+    conv2        = TimeDistributed(
+                        Conv2D(
+                            64, 
+                            kernel_size = (5, 5), 
+                            padding     = 'same', # zero-padding
+                            strides     = (2, 2), 
+                            name        = 'conv2'
+                        )
+                    )(conv1)
+
     conv2        = TimeDistributed(BatchNormalization())(conv2)
     conv2        = TimeDistributed(Activation('relu'))(conv2)
 
+    # LSTM layers
     convlstm1 = ConvLSTM2D(64, kernel_size=(3, 3), padding='same', return_sequences=True, name='convlstm1')(conv2)
     convlstm2 = ConvLSTM2D(32, kernel_size=(3, 3), padding='same', return_sequences=True, name='convlstm2')(convlstm1)
     convlstm3 = ConvLSTM2D(64, kernel_size=(3, 3), padding='same', return_sequences=True, name='convlstm3')(convlstm2)
 
+    # De-convolution layers
     deconv1 = TimeDistributed(Conv2DTranspose(128, kernel_size=(5, 5), padding='same', strides=(2, 2), name='deconv1'))(convlstm3)
     deconv1 = TimeDistributed(BatchNormalization())(deconv1)
     deconv1 = TimeDistributed(Activation('relu'))(deconv1)
@@ -55,7 +77,7 @@ def compile_model(model, loss, optimizer):
     model.compile(loss=loss, optimizer=opt)
 
 
-def train(dataset, job_folder, logger, video_root_path='/share/data/videos'):
+def train(dataset, job_folder, logger, video_root_path='./data/videos'):
     """Build and train the model
     """
     import yaml
@@ -66,6 +88,7 @@ def train(dataset, job_folder, logger, video_root_path='/share/data/videos'):
     from   keras.utils.io_utils import HDF5Matrix
 
     logger.debug("Loading configs from {}".format(os.path.join(job_folder, 'config.yml')))
+
     with open(os.path.join(job_folder, 'config.yml'), 'r') as ymlfile:
         cfg = yaml.load(ymlfile)
 
@@ -74,9 +97,8 @@ def train(dataset, job_folder, logger, video_root_path='/share/data/videos'):
     loss        = cfg['cost']
     optimizer   = cfg['optimizer']
     time_length = cfg['time_length']
-    # shuffle = cfg['shuffle']
 
-    logger.info("Building model of type {} and activation {}".format(model_type, activation))
+    # logger.info("Building model of type {} and activation {}".format(model_type, activation))
     model = get_model(time_length)
     logger.info("Compiling model with {} and {} optimizer".format(loss, optimizer))
     compile_model(model, loss, optimizer)
@@ -99,7 +121,8 @@ def train(dataset, job_folder, logger, video_root_path='/share/data/videos'):
     logger.info("Initializing training...")
 
     history = model.fit(
-        data, data,
+        data, # X 
+        data, # Y (Same as input for Auto-encoder)
         batch_size       = batch_size,
         epochs           = nb_epoch,
         validation_split = 0.15,
@@ -130,9 +153,9 @@ def get_gt_vid(dataset, vid_idx, pred_vid):
     import numpy as np
 
     if dataset in ("indoor", "plaza", "lawn"):
-        gt_vid = np.load('/share/data/groundtruths/{0}_test_gt.npy'.format(dataset))
+        gt_vid = np.load('./data/groundtruths/{0}_test_gt.npy'.format(dataset))
     else:
-        gt_vid_raw = np.loadtxt('/share/data/groundtruths/gt_{0}_vid{1:02d}.txt'.format(dataset, vid_idx+1))
+        gt_vid_raw = np.loadtxt('./data/groundtruths/gt_{0}_vid{1:02d}.txt'.format(dataset, vid_idx+1))
         gt_vid = np.zeros_like(pred_vid)
 
         try:
@@ -198,24 +221,23 @@ def calc_auc_overall(logger, dataset, n_vid, save_path):
 
 
 def test(logger, dataset, t, job_uuid, epoch, val_loss, visualize_score=True, visualize_frame=False,
-         video_root_path='/share/data/videos'):
+         video_root_path='./data/videos'):
-    import numpy as np
-    from keras.models import load_model
     import os
     import h5py
+    import numpy                as     np
+    from   keras.models         import load_model
     from   keras.utils.io_utils import HDF5Matrix
     import matplotlib.pyplot    as     plt
     from   scipy.misc           import imresize
 
-    n_videos = {'avenue': 21, 'enter': 6, 'exit': 4, 'ped1': 36, 'ped2': 12}
+    n_videos       = {'avenue': 1}
     test_dir       = os.path.join(video_root_path, '{0}/testing_h5_t{1}'.format(dataset, t))
-    job_folder = os.path.join('/share/clean/{}/jobs'.format(dataset), job_uuid)
+    job_folder     = os.path.join('./data/clean/{}/jobs'.format(dataset), job_uuid)
     model_filename = 'model_snapshot_e{:03d}_{:.6f}.h5'.format(epoch, val_loss)
     temporal_model = load_model(os.path.join(job_folder, model_filename))
     save_path      = os.path.join(job_folder, 'result')
     os.makedirs(save_path, exist_ok=True)
 
-
     for videoid in range(n_videos[dataset]):
         videoname = '{0}_{1:02d}.h5'.format(dataset, videoid+1)
         filepath  = os.path.join(test_dir, videoname)
@@ -224,7 +246,7 @@ def test(logger, dataset, t, job_uuid, epoch, val_loss, visualize_score=True, vi
         filesize  = f['data'].shape[0]
         f.close()
 
-        gt_vid_raw = np.loadtxt('/share/data/groundtruths/gt_{0}_vid{1:02d}.txt'.format(dataset, videoid+1))
+        # gt_vid_raw = np.loadtxt('./data/groundtruths/gt_{0}_vid{1:02d}.txt'.format(dataset, videoid+1))
 
         logger.debug("Predicting using {}".format(os.path.join(job_folder, model_filename)))
         X_test = HDF5Matrix(filepath, 'data')
@@ -269,17 +291,17 @@ def test(logger, dataset, t, job_uuid, epoch, val_loss, visualize_score=True, vi
             plt.ylim(0, 1)
             plt.xlim(1, score_vid.shape[0]+1)
 
-            try:
+            # try:
-                for event in range(gt_vid_raw.shape[1]):
+            #     for event in range(gt_vid_raw.shape[1]):
-                    start = int(gt_vid_raw[0, event])
+            #         start = int(gt_vid_raw[0, event])
-                    end = int(gt_vid_raw[1, event]) + 1
+            #         end = int(gt_vid_raw[1, event]) + 1
-                    gt_vid[start:end] = 1
+            #         gt_vid[start:end] = 1
-                    plt.fill_between(np.arange(start, end), 0, 1, facecolor='red', alpha=0.4)
+            #         plt.fill_between(np.arange(start, end), 0, 1, facecolor='red', alpha=0.4)
-            except IndexError:
+            # except IndexError:
-                start = int(gt_vid_raw[0])
+            #     start = int(gt_vid_raw[0])
-                end = int(gt_vid_raw[1])
+            #     end = int(gt_vid_raw[1])
-                gt_vid[start:end] = 1
+            #     gt_vid[start:end] = 1
-                plt.fill_between(np.arange(start, end), 0, 1, facecolor='red', alpha=0.4)
+            #     plt.fill_between(np.arange(start, end), 0, 1, facecolor='red', alpha=0.4)
 
             plt.savefig(os.path.join(save_path, 'scores_{0}_video_{1:02d}.png'.format(dataset, videoid+1)), dpi=300)
             plt.close()
@@ -305,5 +327,5 @@ def test(logger, dataset, t, job_uuid, epoch, val_loss, visualize_score=True, vi
                 plt.clf()
 
     logger.info("{}: Calculating overall metrics".format(dataset))
-    auc_overall, eer_overall = calc_auc_overall(logger, dataset, n_videos[dataset], save_path)
+    # auc_overall, eer_overall = calc_auc_overall(logger, dataset, n_videos[dataset], save_path)
 

config.yml

@@ -1,5 +1,5 @@
-time_length: 8
+time_length: 4
 cost: mse
-epochs: 2000
+epochs: 2
 optimizer: sgd
 batch_size: 16

convert_video_to_frame.py

@@ -3,12 +3,14 @@ import skvideo.io
 from skimage.transform import resize
 from skimage.io import imsave
 
-video_root_path = '/share/data/videos'
+video_root_path = './data/videos'
 size = (224, 224)
 
 def video_to_frame(dataset, train_or_test):
     video_path = os.path.join(video_root_path, dataset, '{}_videos'.format(train_or_test))
     frame_path = os.path.join(video_root_path, dataset, '{}_frames'.format(train_or_test))
+    print('video_path = ', video_path)
+    print('frame_path = ', frame_path)
     os.makedirs(frame_path, exist_ok=True)
 
     for video_file in os.listdir(video_path):
@@ -23,22 +25,6 @@ def video_to_frame(dataset, train_or_test):
               imsave(os.path.join(vid_frame_path, '{:05d}.jpg'.format(count)), image)     # save frame as JPEG file
               count += 1
 
-# avenue
+# convert
 video_to_frame('avenue', 'training')
 video_to_frame('avenue', 'testing')
-
-# ped1
-video_to_frame('ped1', 'training')
-video_to_frame('ped1', 'testing')
-
-# ped2
-video_to_frame('ped2', 'training')
-video_to_frame('ped2', 'testing')
-
-# enter
-video_to_frame('enter', 'training')
-video_to_frame('enter', 'testing')
-
-# exit
-video_to_frame('exit', 'training')
-video_to_frame('exit', 'testing')

dataset.py

@@ -1,5 +1,5 @@
 
-def calc_mean(dataset, video_root_path='/share/data/videos'):
+def calc_mean(dataset, video_root_path='./data/videos'):
     import os
     from skimage.io import imread
     import numpy as np
@@ -22,7 +22,7 @@ def calc_mean(dataset, video_root_path='/share/data/videos'):
     np.save(os.path.join(video_root_path, dataset, 'mean_frame_224.npy'), frame_mean)
 
 
-def subtract_mean(dataset, video_root_path='/share/data/videos'):
+def subtract_mean(dataset, video_root_path='./data/videos'):
     import os
     from skimage.io import imread
     import numpy as np
@@ -56,7 +56,7 @@ def subtract_mean(dataset, video_root_path='/share/data/videos'):
         np.save(os.path.join(video_root_path, dataset, 'testing_frames_{}.npy'.format(frame_folder)), testing_frames_vid)
 
 
-def build_h5(dataset, train_or_test, t, video_root_path='/share/data/videos'):
+def build_h5(dataset, train_or_test, t, video_root_path='./data/videos'):
     import h5py
     from tqdm import tqdm
     import os
@@ -87,7 +87,7 @@ def build_h5(dataset, train_or_test, t, video_root_path='/share/data/videos'):
     build_volume(train_or_test, num_videos, time_length=t)
 
 
-def combine_dataset(dataset, t, video_root_path='/share/data/videos'):
+def combine_dataset(dataset, t, video_root_path='./data/videos'):
     import h5py
     import os
     from tqdm import tqdm
@@ -121,7 +121,7 @@ def combine_dataset(dataset, t, video_root_path='/share/data/videos'):
     output_file.close()
 
 
-def preprocess_data(logger, dataset, t, video_root_path='/share/data/videos'):
+def preprocess_data(logger, dataset, t, video_root_path='./data/videos'):
     import os
 
     # Step 1: Calculate the mean frame of all training frames
@@ -167,6 +167,8 @@ def preprocess_data(logger, dataset, t, video_root_path='/share/data/videos'):
             num_videos = len(os.listdir(os.path.join(video_root_path, '{}/{}_frames'.format(dataset, train_or_test))))
             for i in range(num_videos):
                 h5_file = os.path.join(video_root_path, '{0}/{1}_h5_t{2}/{0}_{3:02d}.h5'.format(dataset, train_or_test, t, i+1))
+                print('-------------------')
+                print(h5_file)
                 assert(os.path.isfile(h5_file))
         except AssertionError:
             logger.info("Step 3/4: Generating volumes for {} {} set".format(dataset, train_or_test))

start_test.py

@@ -7,15 +7,17 @@ from classifier import test
 
 
 device      = 'cpu'
-dataset = 'ped1'
+dataset     = 'avenue'
-job_uuid = '86f47b9c-d0ca-49a8-beb6-84373ea9e880'
+job_uuid    = '603213fe-3308-41d7-8ce2-d734ea4a547b'
-epoch = 586
+epoch       = 2
-val_loss = 0.001069
+val_loss    = 0.001326
-time_length = 8
+time_length = 4
 
-job_folder = os.path.join('/share/clean/{}/jobs'.format(dataset), job_uuid)
+job_folder  = os.path.join('./data/clean/{}/jobs'.format(dataset), job_uuid)
 log_path    = os.path.join(job_folder, 'logs')
+
 os.makedirs(log_path, exist_ok=True)
+
 logging.basicConfig(filename = os.path.join(log_path, "test-{}.log".format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))),
                     level    = logging.DEBUG,
                     format   = "%(asctime)s [%(levelname)s] %(message)s")

start_train.py

@@ -3,15 +3,15 @@ import datetime
 import os
 import sys
 import coloredlogs
-from classifier import train
 import uuid
+from   classifier import train
 from   shutil     import copyfile
 
-dataset = 'ped1'
+dataset = 'avenue'
-device = 'gpu1'
+device  = 'cpu'
 
 job_uuid = str(uuid.uuid4())
-job_folder = os.path.join('/share/clean/{}/jobs'.format(dataset), job_uuid)
+job_folder = os.path.join('./data/clean/{}/jobs'.format(dataset), job_uuid)
 os.makedirs(job_folder)
 copyfile('config.yml', os.path.join(job_folder, 'config.yml'))
 
@@ -21,6 +21,7 @@ logging.basicConfig(filename=os.path.join(log_path,
                                 "train-{}.log".format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))),
                     level    = logging.DEBUG,
                     format   = "%(asctime)s [%(levelname)s] %(message)s")
+
 coloredlogs.install(level=logging.INFO)
 logger = logging.getLogger()