def depth_predict(opt, image_pathfile='data/depth.txt'):
# opt = TrainOptions().parse() # set CUDA_VISIBLE_DEVICES before import torch
with open(image_pathfile, 'r') as img_file:
img = cv2.imread(img_file.read())
img_shape = [img.shape[0], img.shape[1]]
# print('shape of image:', img_shape)
video_data_loader = aligned_data_loader.DAVISDataLoader(
image_pathfile, BATCH_SIZE)
video_dataset = video_data_loader.load_data()
model = pix2pix_model.Pix2PixModel(opt)
torch.backends.cudnn.enabled = False
torch.backends.cudnn.benchmark = False
model.switch_to_eval()
save_path = 'data/outputs/'
for i, data in enumerate(video_dataset):
print(i)
stacked_img = data[0]
targets = data[1]
pred_d_m = model.run_and_save_DAVIS(stacked_img, targets, save_path,
img_shape)
return pred_d_m
# depth = depth_predict()
def run():
# Windows用に追加
torch.multiprocessing.freeze_support()
opt = TrainVmdOptions().parse(
) # set CUDA_VISIBLE_DEVICES before import torch
video_list = 'test_data/test_davis_video_list2.txt'
eval_num_threads = 2
video_data_loader = aligned_data_loader.DAVISDataLoader(
video_list, BATCH_SIZE)
video_dataset = video_data_loader.load_data()
print('========================= Video dataset #images = %d =========' %
len(video_data_loader))
model = pix2pix_model.Pix2PixModel(opt)
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
best_epoch = 0
global_step = 0
print(
'================================= BEGIN VALIDATION ====================================='
)
print('TESTING ON VIDEO')
model.switch_to_eval()
save_path = 'test_data/viz_predictions/'
print('save_path %s' % save_path)
for i, data in enumerate(video_dataset):
print(i)
stacked_img = data[0]
targets = data[1]
model.run_and_save_DAVIS_test(stacked_img, targets, save_path)
# See the License for the specific language governing permissions and
# limitations under the License.
import torch
from options.train_options import TrainOptions
from loaders import aligned_data_loader
from models import pix2pix_model
BATCH_SIZE = 1
opt = TrainOptions().parse() # set CUDA_VISIBLE_DEVICES before import torch
video_list = 'test_data/test_davis_video_list.txt'
eval_num_threads = 2
video_data_loader = aligned_data_loader.DAVISDataLoader(video_list, BATCH_SIZE)
video_dataset = video_data_loader.load_data()
print('========================= Video dataset #images = %d =========' %
len(video_data_loader))
model = pix2pix_model.Pix2PixModel(opt)
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
best_epoch = 0
global_step = 0
print(
'================================= BEGIN VALIDATION ====================================='
)
def main():
config = {
"apiKey": "AIzaSyBkQ5z8Rs5IRP4lHoiWyXV9XVQHjAh-sEI",
"authDomain": "a-eye-for-the-blind.firebaseapp.com",
"storageBucket": "a-eye-for-the-blind.appspot.com",
"databaseURL":
"https://a-eye-for-the-blind-default-rtdb.firebaseio.com/",
}
uid = "^^^^^^^^^^^" # unique user ID, must set before running
email = '*****@*****.**'
password = '******'
firebase = Firebase(config)
db = firebase.database()
auth = firebase.auth()
storage = firebase.storage()
user = auth.sign_in_with_email_and_password(email, password)
user = auth.refresh(user['refreshToken'])
if uid == "" or email == "" or password == "":
print("Please set user UID, email, or password in the lines above!")
sys.exit()
engine = pyttsx3.init()
BATCH_SIZE = 1
eval_num_threads = 2
opt = TrainOptions().parse(
) # set CUDA_VISIBLE_DEVICES before import torch
model = pix2pix_model.Pix2PixModel(opt)
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
best_epoch = 0
global_step = 0
model.switch_to_eval()
video_list = 'D:/A-Eye For The Blind/2dtodepth/infile1/'
save_path = 'D:/A-Eye For The Blind/2dtodepth/outfile/'
uid = 'yQowLXfAMddiITuMFASMoKlSGyh1'
# initialize the camera
cam = cv2.VideoCapture(cv2.CAP_DSHOW) # 0 -> index of camera
x = 0
while True:
s, img = cam.read()
cv2.imwrite("D:/A-Eye For The Blind/2dtodepth/infile1/filename.jpg",
img) # save image
# filename = uid + ' ' + time()
storage.child(f"images/i{str(x)}.jpg").put(
"D:/A-Eye For The Blind/2dtodepth/infile1/filename.jpg",
user['idToken'])
url = storage.child(f"images/i{str(x)}.jpg").get_url(user['idToken'])
data = {f"i{str(x)}": f"{url}"}
db.child(f"users/{uid}").child("images").update(data)
video_data_loader = aligned_data_loader.DAVISDataLoader(
video_list, BATCH_SIZE)
video_dataset = video_data_loader.load_data()
for i, data in enumerate(video_dataset):
stacked_img = data[0]
targets = data[1]
output = model.run_and_save_DAVIS(stacked_img, targets, save_path)
height, width, _ = output.shape
width_cutoff = width // 2
half1 = output[:, :width_cutoff]
half2 = output[:, width_cutoff:]
width_cutoff = width // 4
s1 = half1[:, :width_cutoff]
s2 = half1[:, width_cutoff:]
s3 = half2[:, :width_cutoff]
s4 = half2[:, width_cutoff:]
commands = finalcommand(s1, s2, s3, s4)
print(commands)
if commands[1] == 0:
if commands[0] == 0 and commands[2] == 0:
engine.say("STOP!")
elif commands[0] == 0:
engine.say("Move right.")
elif commands[2] == 2:
engine.say("Move left.")
else:
engine.say("Move left.")
engine.runAndWait()
os.remove("D:/A-Eye For The Blind/2dtodepth/infile1/filename.jpg")
x += 1
if cv2.waitKey(33) == ord('a'):
break
cam.release()