Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
ResNet50_tensorflow
Commits
35f33abb
Unverified
Commit
35f33abb
authored
Jul 20, 2018
by
pkulzc
Committed by
GitHub
Jul 20, 2018
Browse files
Merge pull request #4851 from tensorflow/achowdhery-patch-2
Updating comments in export_tflite_ssd_graph scripts
parents
61ec6026
8dba5924
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
5 additions
and
5 deletions
+5
-5
research/object_detection/export_tflite_ssd_graph.py
research/object_detection/export_tflite_ssd_graph.py
+2
-2
research/object_detection/export_tflite_ssd_graph_lib.py
research/object_detection/export_tflite_ssd_graph_lib.py
+3
-3
No files found.
research/object_detection/export_tflite_ssd_graph.py
View file @
35f33abb
...
...
@@ -40,10 +40,10 @@ If add_postprocessing_op is true: frozen graph adds a
TFLite_Detection_PostProcess custom op node has four outputs:
detection_boxes: a float32 tensor of shape [1, num_boxes, 4] with box
locations
detection_scores: a float32 tensor of shape [1, num_boxes]
with class scores
detection_classes: a float32 tensor of shape [1, num_boxes]
with class indices
detection_scores: a float32 tensor of shape [1, num_boxes]
with class scores
num_boxes: a float32 tensor of size 1 containing the number of detected boxes
else:
the graph has two outputs:
...
...
research/object_detection/export_tflite_ssd_graph_lib.py
View file @
35f33abb
...
...
@@ -41,7 +41,7 @@ def get_const_center_size_encoded_anchors(anchors):
boxes
Returns:
encoded_anchors: a float32 constant tensor of shape [
4,
num_anchors]
encoded_anchors: a float32 constant tensor of shape [num_anchors
, 4
]
containing the anchor boxes.
"""
anchor_boxlist
=
box_list
.
BoxList
(
anchors
)
...
...
@@ -83,10 +83,10 @@ def append_postprocessing_op(frozen_graph_def, max_detections,
TFLite_Detection_PostProcess custom op node has four outputs:
detection_boxes: a float32 tensor of shape [1, num_boxes, 4] with box
locations
detection_scores: a float32 tensor of shape [1, num_boxes]
with class scores
detection_classes: a float32 tensor of shape [1, num_boxes]
with class indices
detection_scores: a float32 tensor of shape [1, num_boxes]
with class scores
num_boxes: a float32 tensor of size 1 containing the number of detected
boxes
"""
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment