Toggle navigation
Toggle navigation
This project
Loading...
Sign in
2020-2-capstone-design2
/
2015104192
Go to a project
Toggle navigation
Toggle navigation pinning
Projects
Groups
Snippets
Help
Project
Activity
Repository
Pipelines
Graphs
Issues
0
Merge Requests
0
Wiki
Snippets
Network
Create a new issue
Builds
Commits
Issue Boards
Authored by
윤영빈
2020-11-08 21:12:21 +0900
Browse Files
Options
Browse Files
Download
Email Patches
Plain Diff
Commit
31662afe83301c2b7a5ca8756e497b0d558cab36
31662afe
1 parent
756d59d7
changed saving method
Show whitespace changes
Inline
Side-by-side
Showing
8 changed files
with
63 additions
and
31 deletions
web/backend/api/views.py
web/backend/yt8m/F/yt8mDataset/savedModel/model_flags.json
web/backend/yt8m/eval.py
web/backend/yt8m/frame_level_models.py
web/backend/yt8m/inference.py
web/backend/yt8m/inference_per_segment.py
web/backend/yt8m/train.py
web/backend/yt8m/utils.py
web/backend/api/views.py
View file @
31662af
...
...
@@ -93,7 +93,6 @@ class VideoFileUploadView(APIView):
else
:
return
Response
(
file_serializer
.
errors
,
status
=
status
.
HTTP_400_BAD_REQUEST
)
class
VideoFileList
(
APIView
):
def
get_object
(
self
,
pk
):
...
...
web/backend/yt8m/F/yt8mDataset/savedModel/model_flags.json
0 → 100644
View file @
31662af
{
"model"
:
"NetVLADModelLF"
,
"feature_sizes"
:
"1024,128"
,
"feature_names"
:
"rgb,audio"
,
"frame_features"
:
true
,
"label_loss"
:
"CrossEntropyLoss"
}
\ No newline at end of file
web/backend/yt8m/eval.py
View file @
31662af
...
...
@@ -33,17 +33,17 @@ FLAGS = flags.FLAGS
if
__name__
==
"__main__"
:
# Dataset flags.
flags
.
DEFINE_string
(
"train_dir"
,
"F:/yt8mDataset/savedModel"
,
"train_dir"
,
"F:/yt8mDataset/savedModel
aa2
"
,
"The directory to load the model files from. "
"The tensorboard metrics files are also saved to this "
"directory."
)
flags
.
DEFINE_string
(
"eval_data_pattern"
,
""
,
"eval_data_pattern"
,
"
F:/yt8mDataset/train2/train*.tfrecord
"
,
"File glob defining the evaluation dataset in tensorflow.SequenceExample "
"format. The SequenceExamples are expected to have an 'rgb' byte array "
"sequence feature as well as a 'labels' int64 context feature."
)
flags
.
DEFINE_bool
(
"segment_labels"
,
Fals
e
,
"segment_labels"
,
Tru
e
,
"If set, then --eval_data_pattern must be frame-level features (but with"
" segment_labels). Otherwise, --eval_data_pattern must be aggregated "
"video-level features. The model must also be set appropriately (i.e. to "
...
...
@@ -54,7 +54,7 @@ if __name__ == "__main__":
"How many examples to process per batch."
)
flags
.
DEFINE_integer
(
"num_readers"
,
8
,
"How many threads to use for reading input files."
)
flags
.
DEFINE_boolean
(
"run_once"
,
Fals
e
,
"Whether to run eval only once."
)
flags
.
DEFINE_boolean
(
"run_once"
,
Tru
e
,
"Whether to run eval only once."
)
flags
.
DEFINE_integer
(
"top_k"
,
5
,
"How many predictions to output per video."
)
...
...
web/backend/yt8m/frame_level_models.py
View file @
31662af
...
...
@@ -46,7 +46,7 @@ flags.DEFINE_string(
"Some Frame-Level models can be decomposed into a "
"generalized pooling operation followed by a "
"classifier layer"
)
flags
.
DEFINE_integer
(
"lstm_cells"
,
512
,
"Number of LSTM cells."
)
flags
.
DEFINE_integer
(
"lstm_cells"
,
1024
,
"Number of LSTM cells."
)
flags
.
DEFINE_integer
(
"lstm_layers"
,
2
,
"Number of LSTM layers."
)
...
...
web/backend/yt8m/inference.py
View file @
31662af
...
...
@@ -23,7 +23,7 @@ import tarfile
import
tempfile
import
time
import
numpy
as
np
import
ssl
import
readers
from
six.moves
import
urllib
import
tensorflow
as
tf
...
...
@@ -39,11 +39,11 @@ FLAGS = flags.FLAGS
if
__name__
==
"__main__"
:
# Input
flags
.
DEFINE_string
(
"train_dir"
,
""
,
"The directory to load the model files from. We assume "
"train_dir"
,
"
/mnt/f/yt8mDataset/savedModelaa
"
,
"The directory to load the model files from. We assume "
"that you have already run eval.py onto this, such that "
"inference_model.* files already exist."
)
flags
.
DEFINE_string
(
"input_data_pattern"
,
""
,
"input_data_pattern"
,
"
/mnt/f/yt8mDataset/train2/train*.tfrecord
"
,
"File glob defining the evaluation dataset in tensorflow.SequenceExample "
"format. The SequenceExamples are expected to have an 'rgb' byte array "
"sequence feature as well as a 'labels' int64 context feature."
)
...
...
@@ -60,7 +60,7 @@ if __name__ == "__main__":
"be created and the contents of the .tgz file will be "
"untarred here."
)
flags
.
DEFINE_bool
(
"segment_labels"
,
Fals
e
,
"segment_labels"
,
Tru
e
,
"If set, then --input_data_pattern must be frame-level features (but with"
" segment_labels). Otherwise, --input_data_pattern must be aggregated "
"video-level features. The model must also be set appropriately (i.e. to "
...
...
@@ -69,18 +69,18 @@ if __name__ == "__main__":
"Limit total number of segment outputs per entity."
)
flags
.
DEFINE_string
(
"segment_label_ids_file"
,
"
https://raw.githubusercontent.com/google/youtube-8m/master/segment_label_ids
.csv"
,
"
/mnt/e/khuhub/2015104192/web/backend/yt8m/vocabulary
.csv"
,
"The file that contains the segment label ids."
)
# Output
flags
.
DEFINE_string
(
"output_file"
,
""
,
"The file to save the predictions to."
)
flags
.
DEFINE_string
(
"output_file"
,
"
/mnt/f/yt8mDataset/kaggle_solution_validation_temp.csv
"
,
"The file to save the predictions to."
)
flags
.
DEFINE_string
(
"output_model_tgz"
,
""
,
"If given, should be a filename with a .tgz extension, "
"the model graph and checkpoint will be bundled in this "
"gzip tar. This file can be uploaded to Kaggle for the "
"top 10 participants."
)
flags
.
DEFINE_integer
(
"top_k"
,
20
,
"How many predictions to output per video."
)
flags
.
DEFINE_integer
(
"top_k"
,
5
,
"How many predictions to output per video."
)
# Other flags.
flags
.
DEFINE_integer
(
"batch_size"
,
512
,
...
...
@@ -108,18 +108,15 @@ def format_lines(video_ids, predictions, top_k, whitelisted_cls_mask=None):
def
get_input_data_tensors
(
reader
,
data_pattern
,
batch_size
,
num_readers
=
1
):
"""Creates the section of the graph which reads the input data.
Args:
reader: A class which parses the input data.
data_pattern: A 'glob' style path to the data files.
batch_size: How many examples to process at a time.
num_readers: How many I/O threads to use.
Returns:
A tuple containing the features tensor, labels tensor, and optionally a
tensor containing the number of frames per video. The exact dimensions
depend on the reader being used.
Raises:
IOError: If no files matching the given pattern were found.
"""
...
...
@@ -243,6 +240,12 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
whitelisted_cls_mask
=
np
.
zeros
((
predictions_tensor
.
get_shape
()[
-
1
],),
dtype
=
np
.
float32
)
segment_label_ids_file
=
FLAGS
.
segment_label_ids_file
"""
if segment_label_ids_file.startswith("http"):
logging.info("Retrieving segment ID whitelist files from
%
s...",
segment_label_ids_file)
segment_label_ids_file, _ = urllib.request.urlretrieve(segment_label_ids_file)
"""
if
segment_label_ids_file
.
startswith
(
"http"
):
logging
.
info
(
"Retrieving segment ID whitelist files from
%
s..."
,
segment_label_ids_file
)
...
...
@@ -307,6 +310,7 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
heaps
=
{}
out_file
.
seek
(
0
,
0
)
for
line
in
out_file
:
print
(
line
)
segment_id
,
preds
=
line
.
decode
(
"utf8"
)
.
split
(
","
)
if
segment_id
==
"VideoId"
:
# Skip the headline.
...
...
web/backend/yt8m/inference_per_segment.py
View file @
31662af
...
...
@@ -41,11 +41,11 @@ FLAGS = flags.FLAGS
if
__name__
==
"__main__"
:
# Input
flags
.
DEFINE_string
(
"train_dir"
,
""
,
"The directory to load the model files from. We assume "
"train_dir"
,
"
E:/savedModel
"
,
"The directory to load the model files from. We assume "
"that you have already run eval.py onto this, such that "
"inference_model.* files already exist."
)
flags
.
DEFINE_string
(
"input_data_pattern"
,
""
,
"input_data_pattern"
,
"
F:/yt8mDataset/test/train*.tfrecord
"
,
"File glob defining the evaluation dataset in tensorflow.SequenceExample "
"format. The SequenceExamples are expected to have an 'rgb' byte array "
"sequence feature as well as a 'labels' int64 context feature."
)
...
...
@@ -62,7 +62,7 @@ if __name__ == "__main__":
"be created and the contents of the .tgz file will be "
"untarred here."
)
flags
.
DEFINE_bool
(
"segment_labels"
,
Fals
e
,
"segment_labels"
,
Tru
e
,
"If set, then --input_data_pattern must be frame-level features (but with"
" segment_labels). Otherwise, --input_data_pattern must be aggregated "
"video-level features. The model must also be set appropriately (i.e. to "
...
...
@@ -75,7 +75,7 @@ if __name__ == "__main__":
"The file that contains the segment label ids."
)
# Output
flags
.
DEFINE_string
(
"output_file"
,
""
,
"The file to save the predictions to."
)
flags
.
DEFINE_string
(
"output_file"
,
"
F:/yt8mDataset/kaggle_solution_validation_temp.csv
"
,
"The file to save the predictions to."
)
flags
.
DEFINE_string
(
"output_model_tgz"
,
""
,
"If given, should be a filename with a .tgz extension, "
...
...
@@ -85,7 +85,7 @@ if __name__ == "__main__":
flags
.
DEFINE_integer
(
"top_k"
,
5
,
"How many predictions to output per video."
)
# Other flags.
flags
.
DEFINE_integer
(
"batch_size"
,
32
,
flags
.
DEFINE_integer
(
"batch_size"
,
16
,
"How many examples to process per batch."
)
flags
.
DEFINE_integer
(
"num_readers"
,
1
,
"How many threads to use for reading input files."
)
...
...
@@ -269,6 +269,7 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
except
ValueError
:
# Simply skip the non-integer line.
continue
fobj
.
close
()
out_file
.
write
(
u"VideoId,LabelConfidencePairs
\n
"
.
encode
(
"utf8"
))
...
...
@@ -286,8 +287,10 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
vocabs
.
close
()
try
:
while
not
coord
.
should_stop
():
print
(
"CAME IN"
)
video_id_batch_val
,
video_batch_val
,
num_frames_batch_val
=
sess
.
run
(
[
video_id_batch
,
video_batch
,
num_frames_batch
])
print
(
"SESS OUT"
)
if
FLAGS
.
segment_labels
:
results
=
get_segments
(
video_batch_val
,
num_frames_batch_val
,
5
)
video_segment_ids
=
results
[
"video_segment_ids"
]
...
...
@@ -333,6 +336,7 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
segment_classes
=
[]
cls_result_arr
=
[]
cls_score_dict
=
{}
resultList
=
[]
out_file
.
seek
(
0
,
0
)
old_seg_name
=
'0000'
counter
=
0
...
...
@@ -344,12 +348,30 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
if
segment_id
==
"VideoId"
:
# Skip the headline.
continue
print
(
line
)
preds
=
preds
.
split
(
" "
)
"""
pred_cls_ids = [int(preds[idx]) for idx in range(0, len(preds), 2)]
pred_cls_scores = [float(preds[idx]) for idx in range(1, len(preds), 2)]
"""
"""
denom = 1.0
for i in range(0,top_k):
denom = denom + float(preds[(i*2) + 1])
print("DENOM = ",denom)
for i in range(0,top_k):
preds[(i*2) + 1] = float(preds[(i*2) + 1])/denom
"""
segment_id
=
"{0}_{1}"
.
format
(
str
(
segment_id
.
split
(
":"
)[
0
]),
str
(
int
(
segment_id
.
split
(
":"
)[
1
])
/
5
))
resultList
.
append
(
"{0},{1},{2},{3},{4},{5}"
.
format
(
segment_id
,
preds
[
0
]
+
","
+
str
(
preds
[
1
]),
preds
[
2
]
+
","
+
str
(
preds
[
3
]),
preds
[
4
]
+
","
+
str
(
preds
[
5
]),
preds
[
6
]
+
","
+
str
(
preds
[
7
]),
preds
[
8
]
+
","
+
str
(
preds
[
9
])))
#=======================================
segment_id
=
str
(
segment_id
.
split
(
":"
)[
0
])
"""
if segment_id not in segment_id_list:
segment_id_list.append(str(segment_id))
segment_classes.append("")
...
...
@@ -372,12 +394,12 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
cls_arr = item.split(" ")[:-1]
cls_arr = list(map(int,cls_arr))
cls_arr
=
sorted
(
cls_arr
)
#
클래스별로 정렬
cls_arr = sorted(cls_arr) #
sort by class
result_string = ""
temp = cls_score_dict[segs]
temp
=
sorted
(
temp
.
items
(),
key
=
operator
.
itemgetter
(
1
),
reverse
=
True
)
#
밸류값 기준으로 정렬
temp= sorted(temp.items(), key=operator.itemgetter(1), reverse=True) #
sort by value
demoninator = float(temp[0][1] + temp[1][1] + temp[2][1] + temp[3][1] + temp[4][1])
#for item in temp:
for itemIndex in range(0, top_k):
...
...
@@ -387,11 +409,16 @@ def inference(reader, train_dir, data_pattern, out_file_location, batch_size,
result_string = result_string + normalized_tag + ":" + format(temp[itemIndex][1]/demoninator,".3f") + ","
cls_result_arr.append(result_string[:-1])
logging
.
info
(
segs
+
" : "
+
result_string
[:
-
1
])
#logging.info(segs + " : " + result_string[:-1])
#=======================================
final_out_file.write("vid_id,segment1,segment2,segment3,segment4,segment5
\n
")
for seg_id, class_indcies in zip(segment_id_list, cls_result_arr):
final_out_file.write("
%
s,
%
s
\n
"
%
(seg_id, str(class_indcies)))
"""
final_out_file
.
write
(
"vid_id,segment1,pred1,segment2,pred2,segment3,pred3,segment4,pred4,segment5,pred5
\n
"
)
for
resultInfo
in
resultList
:
final_out_file
.
write
(
resultInfo
)
final_out_file
.
close
()
out_file
.
close
()
...
...
@@ -410,7 +437,7 @@ def main(unused_argv):
os
.
makedirs
(
FLAGS
.
untar_model_dir
)
tarfile
.
open
(
FLAGS
.
input_model_tgz
)
.
extractall
(
FLAGS
.
untar_model_dir
)
FLAGS
.
train_dir
=
FLAGS
.
untar_model_dir
print
(
"TRAIN DIR "
,
FLAGS
.
input_data_pattern
)
flags_dict_file
=
os
.
path
.
join
(
FLAGS
.
train_dir
,
"model_flags.json"
)
if
not
file_io
.
file_exists
(
flags_dict_file
):
raise
IOError
(
"Cannot find
%
s. Did you run eval.py?"
%
flags_dict_file
)
...
...
web/backend/yt8m/train.py
View file @
31662af
...
...
@@ -75,7 +75,7 @@ if __name__ == "__main__":
flags
.
DEFINE_integer
(
"num_gpu"
,
1
,
"The maximum number of GPU devices to use for training. "
"Flag only applies if GPUs are installed"
)
flags
.
DEFINE_integer
(
"batch_size"
,
64
,
flags
.
DEFINE_integer
(
"batch_size"
,
16
,
"How many examples to process per batch for training."
)
flags
.
DEFINE_string
(
"label_loss"
,
"CrossEntropyLoss"
,
"Which loss function to use for training the model."
)
...
...
@@ -94,13 +94,13 @@ if __name__ == "__main__":
"Multiply current learning rate by learning_rate_decay "
"every learning_rate_decay_examples."
)
flags
.
DEFINE_integer
(
"num_epochs"
,
5
,
"How many passes to make over the dataset before "
"num_epochs"
,
100
,
"How many passes to make over the dataset before "
"halting training."
)
flags
.
DEFINE_integer
(
"max_steps"
,
None
,
"max_steps"
,
100
,
"The maximum number of iterations of the training loop."
)
flags
.
DEFINE_integer
(
"export_model_steps"
,
5
,
"export_model_steps"
,
10
,
"The period, in number of steps, with which the model "
"is exported for batch prediction."
)
...
...
web/backend/yt8m/utils.py
View file @
31662af
...
...
@@ -154,6 +154,7 @@ def GetListOfFeatureNamesAndSizes(feature_names, feature_sizes):
List of the feature names and list of the dimensionality of each feature.
Elements in the first/second list are strings/integers.
"""
feature_sizes
=
str
(
feature_sizes
)
list_of_feature_names
=
[
feature_names
.
strip
()
for
feature_names
in
feature_names
.
split
(
","
)
]
...
...
Please
register
or
login
to post a comment