network_name=args.network_name,
checkpoint_path=args.checkpoint,
batch_size=args.batch_size,
num_classes=args.num_classes,
preproc_func_name=args.preproc_func,
preproc_threads=args.num_preproc_threads)
# Print the network summary, use these layer names for feature extraction
#feature_extractor.print_network_summary()
# Feature extraction example using a filename queue to feed images
feature_dataset = feature_extraction_queue(feature_extractor,
args.image_path, layer_names,
args.batch_size,
args.num_classes)
# print(type(feature_dataset))
# for i in feature_dataset:
# print(i)
data = feature_dataset['resnet_v2_101/logits']
data = np.reshape(data, [data.shape[0], data.shape[3]])
np.save(args.out_file, data)
# Write features to disk as HDF5 file
utils.write_hdf5('features.h5', layer_names, feature_dataset)
print("Successfully written features to: {}".format(args.out_file))
# Close the threads and close session.
feature_extractor.close()
print("Finished.")
def run_video(file_path=None):
shutil.rmtree('tmp/')
os.mkdir('tmp/')
batch_size = 1
with h5py.File('/data1/Project/TF_FeatureExtraction/features.h5','r') as f:
criterion = f['resnet_v2_101']['logits'].value.squeeze(axis=1).squeeze(axis=1) #[N,d]
feature_extractor = FeatureExtractor(
network_name='resnet_v2_101',
checkpoint_path='/data1/Project/TF_FeatureExtraction/checkpoints/resnet_v2_101.ckpt',
batch_size=batch_size,
num_classes=1001,
preproc_func_name='inception',
preproc_threads=2
)
FLAG = False
keypoints_track = []
if not file_path:
file_path = 0
cap = cv2.VideoCapture(file_path)
out = cv2.VideoWriter('output.avi', cv2.VideoWriter_fourcc('M','J','P','G'), 15, (int(cap.get(3)), int(cap.get(4))))
while 1:
t = cv2.getTickCount()
# Read new image
ret, frame = cap.read()
#cv2.imwrite('screenshot.jpg', frame)
if not ret:
break
# Output keypoints and the image with the human skeleton blended on it
keypoints, output_image = openpose.forward(frame, True)
#keypoints_track.append(keypoints)
for i in range(keypoints.shape[0]):
#boxes = body_parts_box(keypoints[i,:,:])
box = upper_body_box(keypoints[i,:,:])
if box is None:
continue
if box[0][0] <=0 or box[0][1] <= 0 or box[1][0] <= 0 or box[1][1] <=0:
print(keypoints[i,:,:])
FLAG = True
cv2.imwrite('tmp/p%d.jpg'%i, frame[box[0][1]:box[1][1]+1, box[0][0]:box[1][0]+1, :])
feature_data = feature_extraction_queue(feature_extractor, 'tmp/p%d.jpg'%i,
['resnet_v2_101/logits'], batch_size, num_classes=1001)
feature = feature_data['resnet_v2_101/logits'].squeeze(axis=1).squeeze(axis=1)
score = check_police(feature, criterion)
if score >= 0.5: # is police
color = (255, 0, 0)
else:
color = (0, 0, 255)
shutil.rmtree('tmp/')
os.mkdir('tmp/')
cv2.rectangle(output_image, box[0], box[1], color, 2)
#if score >= 0.5:
# cv2.imwrite('police_uniform/%s.jpg' % str(time.time()).replace('.', ''), frame[box[0][1]:box[1][1]+1, box[0][0]:box[1][0]+1, :])
cv2.putText(output_image, "%.3f"%score, box[0], cv2.FONT_HERSHEY_SIMPLEX, 0.4, (255,255,255))
#cv2.drawContours(output_image, [box], 0, (0,0,255), 2)
#for bb in boxes:
# if not bb:
# continue
# cv2.rectangle(output_image, bb[0], bb[1], (0, 0, 255), 2)
#for i in range(keypoints.shape[0]):
# detect_action(keypoins[i,:,:])
out.write(output_image)
# Compute FPS
t = (cv2.getTickCount() - t)/cv2.getTickFrequency()
fps = 1.0 / t
cv2.putText(output_image, "%.1f FPS"%fps, (5, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,255,255))
# Display the image
cv2.imshow("output", output_image)
if FLAG:
key = cv2.waitKey(0)
if key == ord(' '):
FLAG = False
continue
if cv2.waitKey(1) & 0xFF == ord('q'):
break
feature_extractor.close()
cap.release()
out.release()
cv2.destroyAllWindows()