import frame_dataloader
from evaluation import legacy_load_model
from evaluation.evaluation import *
from utils.drive_manager import DriveManager
#####################################################
feature_field_size = 2048
testing_samples_per_video = 19
#####################################################
"""Managed"""
evaluate = False
generate_test = False
drive_manager = DriveManager("motion_feature_dataset")
drive_manager.download_file(
'1O8OM6Q01az_71HdMQmWM3op1qJhfsQoI',
"motion.zip") # the id of the zip file contains my network
motion_model_restored = legacy_load_model(
filepath="motion.h5",
custom_objects={
'sparse_categorical_cross_entropy_loss':
sparse_categorical_cross_entropy_loss,
"acc_top_1": acc_top_1,
"acc_top_5": acc_top_5
})
motion_model_restored.summary()
# xception here is a layer
# The architecture summary is
# input_image > batch_norm > xception layer
xception_rebuilt = Model(
import frame_dataloader
from evaluation import legacy_load_model
from evaluation.evaluation import *
from utils.drive_manager import DriveManager
#####################################################
feature_field_size = 2048
testing_samples_per_video = 19
#####################################################
"""Managed"""
evaluate = False
generate_test = False
drive_manager = DriveManager("spatial_feature_dataset")
drive_manager.download_file('17O8JdvaSNJFmbvZtQPIBYNLgM9Um-znf', "spatial.zip")
spatial_model_restored = legacy_load_model(
filepath="spatial.h5",
custom_objects={
'sparse_categorical_cross_entropy_loss':
sparse_categorical_cross_entropy_loss,
"acc_top_1": acc_top_1,
"acc_top_5": acc_top_5
})
spatial_model_restored.summary()
spatial_model_with_2_outputs = Model(
spatial_model_restored.inputs, # input image
[layer.output for layer in spatial_model_restored.layers[-2:]
] # visual features, softmax output
"train_features_spatial.pickle")
if len(test_spatial) == 0:
print(
"Please run 'generate_spatial_feature_dataset.py' and generate 'test_features_spatial.pickle'..this file will be saved to your drive in '<YOUR FOLDER:{}>/spatial_feature_dataset'"
.format(drive_manager_spatial.personal_dfolder))
exit()
if len(train_spatial) == 0:
print(
"Please run 'generate_spatial_feature_dataset.py' and generate 'train_features_spatial.pickle'..those files will be saved to your drive in '<YOUR FOLDER:{}>/spatial_feature_dataset'"
.format(drive_manager_spatial.personal_dfolder))
exit()
drive_manager_spatial.download_file(test_spatial[0]["id"],
"test_features_spatial.pickle",
unzip=False)
if len(glob.glob("train_features_spatial.pickle*")) != len(train_spatial):
drive_manager_spatial.download_files_list(train_spatial, False, False)
if is_motion:
drive_manager_motion = DriveManager("motion_feature_dataset")
test_motion = drive_manager_motion.search_file(
"test_features_motion.pickle")
train_motion = drive_manager_motion.search_file(
"train_features_motion.pickle")
if len(test_motion) == 0:
print(
"""
********************************
* Created by mohammed-alaa *
********************************
Evaluate motion and spatial streams
"""
import frame_dataloader
from evaluation import legacy_load_model, get_batch_size
from evaluation.evaluation import *
from utils.drive_manager import DriveManager
"""
Evaluate spatial stream
"""
# download
drive_manager = DriveManager("spa-xception-adam-5e-06-imnet")
drive_manager.download_file('1djGzpxAYFvNX-UaQ7ONqDHGgnzc8clBK', "spatial.zip")
# load into ram
print("Spatial stream")
spatial_model_restored = legacy_load_model(
filepath="spatial.h5",
custom_objects={
'sparse_categorical_cross_entropy_loss':
sparse_categorical_cross_entropy_loss,
"acc_top_1": acc_top_1,
"acc_top_5": acc_top_5
})
spatial_model_restored.summary()
# evaluate
_, spatial_test_loader, test_video_level_label = frame_dataloader.SpatialDataLoader(