Skip to content
GitLab
Explore
Projects
Groups
Snippets
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
Matt Harvey
five-video-classification-methods
Commits
0537dd89
Commit
0537dd89
authored
8 years ago
by
Matt Harvey
Browse files
Options
Download
Email Patches
Plain Diff
Remove cruft
parent
ffe5d230
master
add-demo-script
github/fork/Anner-deJong/patch-2
github/fork/ideaRunner/edit_move_file
github/fork/ikvision/master
github/fork/mertia-himanshu/master
github/fork/prabindh/master
github/fork/sanshibayuan/master
playground
playground-add-synthetic
v1.0
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
data.py
+0
-16
data.py
with
0 additions
and
16 deletions
+0
-16
data.py
+
0
-
16
View file @
0537dd89
...
...
@@ -212,19 +212,3 @@ class DataSet():
break
print
(
"%s: %.2f"
%
(
class_prediction
[
0
],
class_prediction
[
1
]))
if
__name__
==
'__main__'
:
from
PIL
import
Image
data
=
DataSet
(
seq_length
=
20
,
class_limit
=
3
)
print
(
data
.
classes
)
gen
=
data
.
frame_generator
(
32
,
'train'
,
'images'
,
False
)
for
x
,
y
in
gen
:
# x should be 32, with each having seq_ength images.
for
j
,
row
in
enumerate
(
x
):
for
i
,
image
in
enumerate
(
row
):
image
*=
255
actual
=
Image
.
fromarray
(
image
.
astype
(
'uint8'
))
actual
.
save
(
'tmp/whatever-'
+
str
(
i
)
+
'.jpg'
)
print
(
y
[
j
])
data
.
print_class_from_prediction
(
y
[
j
])
break
break
This diff is collapsed.
Click to expand it.
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new 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
Menu
Explore
Projects
Groups
Snippets