flownet2-tf
flownet2-tf copied to clipboard
sampepose
How to save the time for loading pre-trained model
Hello guys,
Currently, my solution is restore the model every image or frame. It will be very time-consuming. I have tried to load it once, here is the code, in src/net.py:
def test_new_rule(self, checkpoint,graphpoint, cap):
"""Create session and restore weights
"""
ops.reset_default_graph()
g = tf.get_default_graph()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print(graphpoint)
saver = tf.train.import_meta_graph(graphpoint)
saver.restore(sess, checkpoint)
ret, frame = cap.read()
input_a = frame
i = 0
while ret:
ret, frame = cap.read()
if frame is None:
continue
input_b = frame
input_a = cv2.resize(input_a, (384, 512))
input_b = cv2.resize(input_b, (384, 512))
# Convert from RGB -> BGR
input_a = input_a[..., [2, 1, 0]]
input_b = input_b[..., [2, 1, 0]]
# Scale from [0, 255] -> [0.0, 1.0] if needed
if input_a.max() > 1.0:
input_a = input_a / 255.0
if input_b.max() > 1.0:
input_b = input_b / 255.0
inputs = {
'input_a': tf.expand_dims(tf.constant(input_a, dtype=tf.float32), 0),
'input_b': tf.expand_dims(tf.constant(input_b, dtype=tf.float32), 0),
}
training_schedule = LONG_SCHEDULE
predictions = self.model(inputs, training_schedule)
#print(predictions)
pred_flow = predictions['flow']
pred_flow = sess.run(pred_flow)[0, :, :, :]
The api is called in src/flownet2/test.py: net = FlowNet2(mode=Mode.TEST) net.test_new_rule( checkpoint='./checkpoints/FlowNet2/flownet-2.ckpt-0', graphpoint='./checkpoints/FlowNet2/flownet-2.ckpt-0.meta', cap=cap )
**Here is error-log:
FailedPreconditionError (see above for traceback): Attempting to use uninitialized value FlowNet2/FlowNetCSS/FlowNetCS/FlowNetC/conv1/weights_1 [[node FlowNet2/FlowNetCSS/FlowNetCS/FlowNetC/conv1/weights_1/read (defined at /root/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/variables.py:277) = IdentityT=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]] [[{{node FlowNet2/ResizeBilinear/_459}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1817_FlowNet2/ResizeBilinear", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]**
It will be very time-consuming for me to restore the model every time for image-processing. Is there a work-around with the varaible definition of flownet-2 that I can transfer to test-file? Thanks & regards!
Building graph should be put out of camera capture loop:
predictions = self.model(inputs, training_schedule)
pred_flow = predictions['flow']
with tf.Session(config=config) as sess:
saver.restore(blablabla)
while ret:
# Get frames and preprocessing
flow = sess.run(pred_flow, feed_dict={
input_a : frame_0,
input_b : frame_1
})[0, :, :, :]
Building graph should be put out of camera capture loop:
predictions = self.model(inputs, training_schedule) pred_flow = predictions['flow'] with tf.Session(config=config) as sess: saver.restore(blablabla) while ret: # Get frames and preprocessing flow = sess.run(pred_flow, feed_dict={ input_a : frame_0, input_b : frame_1 })[0, :, :, :]
Hello, thanks for your guidance,
I write my code like this:
def test_new_rule(self, checkpoint,graphpoint, cap): #Create session and restore weights tf.reset_default_graph() ret, frame = cap.read() input_a = frame input_b = frame input_a = cv2.resize(input_a, (384, 512)) input_b = cv2.resize(input_b, (384, 512)) # Convert from RGB -> BGR input_a = input_a[..., [2, 1, 0]] input_b = input_b[..., [2, 1, 0]] print(input_a.shape) # Scale from [0, 255] -> [0.0, 1.0] if needed if input_a.max() > 1.0: input_a = input_a / 255.0 if input_b.max() > 1.0: input_b = input_b / 255.0 # TODO: This is a hack, we should get rid of this training_schedule = LONG_SCHEDULE inputs = { 'input_a': tf.expand_dims(tf.constant(input_a, dtype=tf.float32), 0), 'input_b': tf.expand_dims(tf.constant(input_b, dtype=tf.float32), 0), } predictions = self.model(inputs, training_schedule) pred_flow = predictions['flow'] saver = tf.train.Saver() with tf.Session() as sess: saver.restore(sess, checkpoint) ret, frame = cap.read() frame_0 = frame i = 0 distance_u = 0 distance_v = 0 maxrad = 0 previous_maxrad = 0 max_maxrad = maxrad increase = False while ret: ret, frame = cap.read() if frame is None: continue frame_1 = frame frame_0 = cv2.resize(frame_0, (384, 512)) frame_1 = cv2.resize(frame_1, (384, 512)) # Convert from RGB -> BGR frame_0 = frame_0[..., [2, 1, 0]] frame_1 = frame_1[..., [2, 1, 0]] # Scale from [0, 255] -> [0.0, 1.0] if needed if frame_0.max() > 1.0: frame_0 = frame_0 / 255.0 if frame_1.max() > 1.0: frame_1= frame_1 / 255.0 frame_0 = tf.convert_to_tensor(frame_0, dtype=tf.float32) frame_1 = tf.convert_to_tensor(frame_1, dtype=tf.float32) flow = sess.run(pred_flow, feed_dict={ input_a : frame_0, input_b : frame_1 })[0, :, :, :] print(flow) print(distance_u) print(distance_v) print(maxrad) max_maxrad = max(max_maxrad, maxrad) if maxrad > previous_maxrad: increase = True else: if increase: increase = False print("Direction changed") print(max_maxrad) previous_maxrad = maxrad frame_0 = frame_1 i = i + 1 if process_video == False: if cv2.waitKey(0) == ord('q'): break
However, it reports that the data-type is not correct:
Traceback (most recent call last):
File "/root/anaconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/root/anaconda3/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/fast/flownet2-tf/src/flownet2/test_find_piano.py", line 54, in
You should feed 2 placeholders to self.model(), instead of 2 constants.
You should feed 2 placeholders to self.model(), instead of 2 constants.
How can I give the 2 placeholders with the input and give it to the self.model and then sess.run()? Looks like pred_flow also depends on the input placeholder. I have tried the different methods, always error?
I haven't trained Flownet2. For inference:
# Build Graph
input_a = tf.placeholder(dtype=tf.float32, shape=[1, None, None, 3])
input_b = tf.placeholder(dtype=tf.float32, shape=[1, None, None, 3])
inputs = {
'input_a': input_a,
'input_b': input_b,
}
training_schedule = LONG_SCHEDULE
predictions = self.model(inputs, training_schedule)
pred_flow = predictions['flow']
with tf.Session(config=config) as sess:
saver.restore(blablabla)
while ret:
# Get frames and preprocessing
# Feed
# There is no need to conver frame(ndarray) to tensor.
flow = sess.run(pred_flow, feed_dict={
input_a : frame_0,
input_b : frame_1
})[0, :, :, :]
This worked for me to measure running time. Change it to handle frames. The code in net.py was changed. (added imports: import cv2 import time from numpy import array)
def test(self, checkpoint, input_a_path, input_b_path, out_path, save_image=True, save_flo=False):
input_a_ = imread(input_a_path)
input_b_ = imread(input_b_path)
tf.reset_default_graph()
input_a_ = cv2.resize(input_a_, dsize=(512, 384))#, interpolation=cv2.INTER_CUBIC)
input_b_ = cv2.resize(input_b_, dsize=(512, 384))#, interpolation=cv2.INTER_CUBIC)
# Convert from RGB -> BGR
input_a_ = input_a_[..., [2, 1, 0]]
input_b_ = input_b_[..., [2, 1, 0]]
# Scale from [0, 255] -> [0.0, 1.0] if needed
if input_a_.max() > 1.0:
input_a_ = input_a_ / 255.0
if input_b_.max() > 1.0:
input_b_ = input_b_ / 255.0
# TODO: This is a hack, we should get rid of this
training_schedule = LONG_SCHEDULE
input_a = tf.placeholder(dtype=tf.float32, shape=[1,384, 512, 3])
input_b = tf.placeholder(dtype=tf.float32, shape=[1,384, 512, 3])
inputs = {
'input_a': input_a,
'input_b': input_b,
}
image1 = array(input_a_).reshape(1, 384, 512, 3)
image2 = array(input_b_).reshape(1, 384, 512, 3)
predictions = self.model(inputs, training_schedule, False)
pred_flow = predictions['flow']
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, checkpoint)
t0=time.time()
for i in range(20):
flow = sess.run(pred_flow, feed_dict={
input_a : image1,
input_b : image2
})[0, :, :, :]
unique_name = 'flow-' + str(uuid.uuid4())
if save_image:
flow_img = flow_to_image(flow)
full_out_path = os.path.join(out_path, unique_name + '.png')
imsave(full_out_path, flow_img)
if save_flo:
full_out_path = os.path.join(out_path, unique_name + '.flo')
write_flow(pred_flow, full_out_path)
print('time for 20 iteration:{}'.format(time.time()-t0))
