Toggle navigation
Toggle navigation
This project
Loading...
Sign in
2020-1-capstone-design1
/
PET_Project1
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
김성주
2020-05-18 22:57:59 +0900
Browse Files
Options
Browse Files
Download
Email Patches
Plain Diff
Commit
dd2c40c2c0e9b8bbd175e8eeca73569c9f28b071
dd2c40c2
1 parent
a87016b1
hot fix for reuse
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
code/yolov3/yolov3.ipynb
code/yolov3/yolov3.ipynb
View file @
dd2c40c
...
...
@@ -1751,7 +1751,7 @@
" ### Model definition
\n
"
,
" yolo_model = yolov3(class_num, anchors, use_label_smooth, use_focal_loss, batch_norm_decay, weight_decay, use_static_shape=False)
\n
"
,
"
\n
"
,
" with tf.variable_scope('yolov3', reuse=
True
):
\n
"
,
" with tf.variable_scope('yolov3', reuse=
tf.AUTO_REUSE
):
\n
"
,
" pred_feature_maps = yolo_model.forward(image, is_training=is_training)
\n
"
,
"
\n
"
,
" loss = yolo_model.compute_loss(pred_feature_maps, y_true)
\n
"
,
...
...
@@ -1989,7 +1989,7 @@
"
\n
"
,
" ### Model definition
\n
"
,
" yolo_model = yolov3(args.class_num, args.anchors)
\n
"
,
" with tf.variable_scope('yolov3', reuse=
True
):
\n
"
,
" with tf.variable_scope('yolov3', reuse=
tf.AUTO_REUSE
):
\n
"
,
" pred_feature_maps = yolo_model.forward(image, is_training=is_training)
\n
"
,
" loss = yolo_model.compute_loss(pred_feature_maps, y_true)
\n
"
,
" y_pred = yolo_model.predict(pred_feature_maps)
\n
"
,
...
...
@@ -2083,7 +2083,7 @@
" with tf.Session() as sess:
\n
"
,
" input_data = tf.placeholder(tf.float32, [1, args.new_size[1], args.new_size[0], 3], name='input_data')
\n
"
,
" yolo_model = yolov3(args.num_class, args.anchors)
\n
"
,
" with tf.variable_scope('yolov3', reuse=
True
):
\n
"
,
" with tf.variable_scope('yolov3', reuse=
tf.AUTO_REUSE
):
\n
"
,
" pred_feature_maps = yolo_model.forward(input_data, False)
\n
"
,
" pred_boxes, pred_confs, pred_probs = yolo_model.predict(pred_feature_maps)
\n
"
,
"
\n
"
,
...
...
Please
register
or
login
to post a comment