return testpreds, testgt
if __name__ == '__main__':
try:
config_dirs_file = sys.argv[1] # directories file
config_file = sys.argv[2] # main params file
except:
print("Config file names not specified, setting them to default namess")
config_dirs_file = "config_dirs.json"
config_file = "config760.json"
print(f'USING CONFIG FILES: config dirs:{config_dirs_file} main config:{config_file}')
C = cs760.loadas_json(config_file)
assert C["s2_classifier_type"] in ['softmax', 'sigmoid'], f"ERROR Invalid s2_classifier_type {C['s2_classifier_type']}. Must be one of 'softmax' or 'sigmoid'."
if C["s2_classifier_type"] == 'sigmoid':
pred_sign = sys.argv[3] # sign to predict if binary classifier
assert pred_sign in C["sign_classes"], "ERROR: Invalid sign to predict: {pred_sign}."
C["curr_sign"] = pred_sign
print(f"TRAINING BINARY CLASSIFIER for sign {C['curr_sign']}")
print("Running with parameters:", C)
Cdirs = cs760.loadas_json(config_dirs_file)
print("Directories:", Cdirs)
C['dirs'] = Cdirs
classes_dict = {}
import copy
import shutil
import cs760 #opencv based utils for vid / image manipulation plus other utilities
try:
video_directory = sys.argv[1] # intput video files
feature_directory = sys.argv[2] # output feature files
except:
print("Video and feature directories not specified, setting them to default locations")
print("Video locations: ../dataset/videos")
print("Feature locations: ../features")
video_directory = "../dataset/videos"
feature_directory = "../features"
C = cs760.loadas_json('config760.json')
print("Running with parameters:", C)
traindir = os.path.join(feature_directory, "train")
valdir = os.path.join(feature_directory, "val")
testdir = os.path.join(feature_directory, "test")
print(f'Creating TRAIN Dir: {traindir}')
os.makedirs(traindir, exist_ok=True) #if dir already exists will continue and WILL NOT delete existing files in that directory
print(f'Creating VAL Dir: {valdir}')
os.makedirs(valdir, exist_ok=True) #if dir already exists will continue and WILL NOT delete existing files in that directory
print(f'Creating TEST Dir: {testdir}')
os.makedirs(testdir, exist_ok=True) #if dir already exists will continue and WILL NOT delete existing files in that directory
if __name__ == '__main__':
try:
config_dirs_file = sys.argv[1] # directories file
config_file = sys.argv[2] # main params file
except:
print("Config file names not specified, setting them to default namess")
config_dirs_file = "config_dirs.json"
config_file = "config760.json"
print(f'USING CONFIG FILES: config dirs:{config_dirs_file} main config:{config_file}')
#print(type(feature_directory))
C = cs760.loadas_json('config760.json')
print("Running with parameters:", C)
Cdirs = cs760.loadas_json(config_dirs_file)
print("Directories:", Cdirs)
C['dirs'] = Cdirs
pkl_directory = C['dirs']['dict_pkls']
#feature_directory = C['dirs']['dict_pkls']
traindir = os.path.join(C['dirs']["dict_pkls"], "train")
valdir = os.path.join(C['dirs']["dict_pkls"], "val")
testdir = os.path.join(C['dirs']["dict_pkls"], "test")
def main():
try:
config_dirs_file = sys.argv[1] # directories file
config_file = sys.argv[2] # main params file
except:
print("Config file names not specified, setting them to default namess")
config_dirs_file = "config_dirs.json"
config_file = "config760.json"
print(f'USING CONFIG FILES: config dirs:{config_dirs_file} main config:{config_file}')
#print(type(feature_directory))
C = cs760.loadas_json('config760.json')
print("Running with parameters:", C)
Cdirs = cs760.loadas_json(config_dirs_file)
print("Directories:", Cdirs)
C['dirs'] = Cdirs
video_directory = C['dirs']['indir']
feature_directory = C['dirs']['outdir']
print(f'Creating feature file Dir: {feature_directory}')
os.makedirs(feature_directory, exist_ok=True) #if dir already exists will continue and WILL NOT delete existing files in that directory
sometimes = lambda aug: iaa.Sometimes(C["augmentation_chance"][0], aug)
sequential_list = [iaa.Sequential([sometimes(iaa.Fliplr(1.0))]), # horizontal flip
iaa.Sequential([sometimes(iaa.Rotate(-5, 5))]), # rotate 5 degrees +/-
iaa.Sequential([sometimes(iaa.CenterCropToAspectRatio(1.15))]),
iaa.Sequential([sometimes(iaa.MultiplyBrightness((2.0, 2.0)))]), # increase brightness
iaa.Sequential([sometimes(iaa.MultiplyHue((0.5, 1.5)))]), # change hue random
iaa.Sequential([sometimes(iaa.RemoveSaturation(1.0))]), # effectively greyscale
iaa.Sequential([sometimes(iaa.pillike.FilterContour())]), # edge detection
iaa.Sequential([sometimes(iaa.AdditiveLaplaceNoise(scale=0.05*255, per_channel=True))]), # add colourful noise
iaa.Sequential([sometimes(iaa.Invert(1))]) # invert colours
]
print("Reading videos from " + video_directory)
print("Outputting features to " + feature_directory)
print("Loading pretrained CNN...")
model = hub.KerasLayer(C["module_url"]) # can be used like any other kera layer including in other layers...
print("Pretrained CNN Loaded OK")
vids = cs760.list_files_pattern(video_directory, C["vid_type"])
print(f'Processing {len(vids)} videos...')
for i, vid in enumerate(vids):
print(f'{i} Processing: {vid}')
vid_np = cs760.get_vid_frames(vid,
video_directory,
writejpgs=False,
writenpy=False,
returnnp=True)
(framecount, frameheight, framewidth, channels) = vid_np.shape
res_key = str(frameheight) + "-" + str(framewidth)
#print(vid, vid_np.shape)
outfile = os.path.splitext(vid)[0]
print(f"Vid frames, h, w, c = {(framecount, frameheight, framewidth, channels)}")
if C["crop_by_res"].get(res_key) is not None:
vid_np_top = cs760.crop_image(vid_np, C["crop_by_res"][res_key])
print(f"Cropped by resolution to {C['crop_by_res'][res_key]}")
else:
vid_np_top = cs760.crop_image(vid_np, C["crop_top"])
print(f"Cropped by default to {C['crop_top']}")
outfile_top = outfile + "__TOP.pkl"
for n in range((len(sequential_list) + 1)):
if n != 0:
vid_aug = sequential_list[n - 1](images=vid_np_top) # augments frames
if type(vid_aug) is list:
vid_aug = np.asarray(vid_aug)
batch = cs760.resize_batch(vid_aug, width=C["expect_img_size"], height=C["expect_img_size"], pad_type='L',
inter=cv2.INTER_CUBIC, BGRtoRGB=False,
simplenormalize=True,
imagenetmeansubtract=False)
temp_outfile = outfile_top[:-4] + C["augmentation_type"][n - 1] + ".pkl"
features = extract(C, model, batch)
cs760.saveas_pickle(features, os.path.join(feature_directory, temp_outfile))
else:
batch = cs760.resize_batch(vid_np_top, width=C["expect_img_size"], height=C["expect_img_size"], pad_type='L',
inter=cv2.INTER_CUBIC, BGRtoRGB=False,
simplenormalize=True,
imagenetmeansubtract=False)
features = extract(C, model, batch)
cs760.saveas_pickle(features, os.path.join(feature_directory, outfile_top))
print(f'Features output shape: {features.shape}')
if C["crop_type"] == 'B': # only for boston vids
vid_np_bot = cs760.crop_image(vid_np, C["crop_bottom"])
outfile_bot = outfile + "__BOT.pkl"
batch = cs760.resize_batch(vid_np_bot, width=C["expect_img_size"], height=C["expect_img_size"], pad_type='L',
inter=cv2.INTER_CUBIC, BGRtoRGB=False,
simplenormalize=True,
imagenetmeansubtract=False)
features = extract(C, model, batch)
cs760.saveas_pickle(features, os.path.join(feature_directory, outfile_bot))
print('Finished outputting features!!')