def test_video(videoPath, model_file):
"""Return the genre type for each video input"""
frames = list(get_frames(videoPath, time_step=1000))
if len(frames) == 0:
print("Error in video")
return
print("Processing", videoPath)
modelName = model_file
model = load_model(model_resource + modelName)
videoFeatures = get_features_batch(frames)
predictedClasses = model.predict_classes(videoFeatures)
predictedScores = model.predict(videoFeatures)
return predictedClasses, predictedScores
def test_video(videoPath):
frames = list(get_frames(videoPath, time_step=1000))
if len(frames)==0:
print("Error in video")
return
print("Processing",videoPath)
modelName = "lstmvgg16_9g_bs32_ep100.h5"
model = load_model("/home/parkhi/Desktop/DIP_project/data/models/"+ modelName)
videoFeatures = get_features_batch(frames)
videoFeatures = np.array(videoFeatures)
videoFeatures = np.reshape(videoFeatures, (videoFeatures.shape[0], 1, videoFeatures.shape[1]))
predictedClasses = model.predict_classes(videoFeatures)
predictedScores = model.predict(videoFeatures)
return predictedClasses, predictedScores
def gather_training_data(genre, model_name=default_model_name):
trainPath = os.path.join(video_resource, 'train', genre)
videoPaths = glob(trainPath + '/*')
genreFeatures = []
for videoPath in videoPaths:
print(videoPath, ":")
frames = list(get_frames(videoPath, time_step=1000))
print(len(frames))
if len(frames) == 0:
print("corrupt.")
continue
videoFeatures = get_features_batch(frames, model_name)
print(videoFeatures.shape)
genreFeatures.append(videoFeatures)
outPath = genre + "_ultimate_" + model_name
dump_pkl(genreFeatures, outPath)
def _get_features_data(mode='val'):
""" deprecated with old dataset """
""" Includes every sample with plotFeatures, videoFeatures, movie_id and genreLabel """
featureData = []
allData = load_pkl(baseName+mode)
plots = []
"""Process plot vectors"""
for data in allData:
movie_id = data['movie_id']
plot = data['plot']
plots.append(plot)
if mode=='train':
textObj = Text()
plotFeatures_all = textObj.fit_transform(plots)
dump_pkl(textObj, 'plot_object_train')
else:
try:
textObj = load_pkl('plot_object_train')
plotFeatures_all = textObj.transform(plots).toarray()
except:
print "Please train the plots first."
return
plotIndex = -1
for data in allData:
plotIndex += 1
movie_id = data['movie_id']
path = glob(video_resource+str(movie_id)+'.*')[0]
plot = data['plot']
genreLabel = data['genreLabel']
print plotIndex,"out of ",len(allData)
print "Gathering features for",movie_id
try:
frames = list(get_frames(path, start_time=1000, end_time=200000, time_step=1000))
videoFeatures = get_features_batch(frames, 'vgg16')
except Exception as e:
print e
continue # Omit the movie if one of the feature is bad
# videoFeatures = None
plotFeatures = plotFeatures_all[plotIndex]
featureData.append({'videoFeatures':videoFeatures, 'plotFeatures':plotFeatures, 'movie_id':movie_id, 'genreLabel':genreLabel})
dump_pkl(featureData, 'feature_data_'+mode)
def gather_genre(genre, limit_videos=100):
print "Gathering features for",genre
videoPaths = glob(video_resource+genre+'/*')[:limit_videos]
genreFeatures = []
for videoPath in videoPaths:
videoFeatures = []
print "extracting features for",videoPath
for frame in get_frames(videoPath, time_step=1000):
frameFeatures = get_features(frame)
videoFeatures.append(frameFeatures)
videoFeatures = np.array(videoFeatures)
genreFeatures.append(videoFeatures)
genreFeatures = np.array(genreFeatures)
print "OK."
print genreFeatures.shape
dump_pkl(genreFeatures, genre+str(limit_videos))
def gather_training_data(genre, model_name=default_model_name):
"""Driver function to collect frame features for a genre"""
trainPath = os.path.join(video_resource,'train',genre)
print trainPath
videoPaths = glob(trainPath+'/*')
genreFeatures = []
for videoPath in videoPaths:
print videoPath,":",
frames =list(get_frames(videoPath, time_step=1000))
print len(frames),
if len(frames)==0:
print "corrupt."
continue
videoFeatures = get_features_batch(frames, model_name)
print videoFeatures.shape
genreFeatures.append(videoFeatures)
outPath = genre+"_ultimate_"+model_name
dump_pkl(genreFeatures, outPath)
def gather_histogram_data(genre, mode='train'):
"""Driver function to collect frame features for a genre"""
trainPath = os.path.join(video_resource, mode, genre)
print trainPath
videoPaths = glob(trainPath + '/*')
genreFeatures = []
for videoPath in videoPaths:
print videoPath, ":",
frames = list(get_frames(videoPath, time_step=1000))
print len(frames),
if len(frames) == 0:
print "corrupt."
continue
videoFeatures = np.array([get_histogram(frame) for frame in frames])
print videoFeatures.shape
genreFeatures.append(videoFeatures)
outPath = genre + "_histogram_" + mode
dump_pkl(genreFeatures, outPath)
def gather_testing_data(genre, model_name=default_model_name):
"""Driver function to collect frame features for a genre"""
testPath = os.path.join(video_resource, 'test', genre)
print(testPath)
videoPaths = glob(testPath + '/*')
genreFeatures = []
for videoPath in videoPaths:
print(
videoPath,
":",
)
frames = list(get_frames(videoPath, time_step=1000))
print(len(frames), )
if len(frames) == 0:
print("corrupt.")
continue
videoFeatures = get_features_batch(frames)
print(videoFeatures.shape)
genreFeatures.append(videoFeatures)
outPath = genre + "_test_" + model_name
dump_pkl(genreFeatures, outPath)
