Comments (3)
python run_lfnet.py --in_dir=images --out_dir=outputs
this one works very well
from lf-net-release.
I tried the notebook codes in ipython. It works. Maybe it is because the jupyter notebook cannot import functions from other folder.
from lf-net-release.
I solved this issue by changing cell 3:
`LOCAL_PATH = '../'
if LOCAL_PATH not in sys.path:
sys.path.append(LOCAL_PATH)
from common.tf_layer_utils import *
from datasets import *
from det_tools import *
from inference import *
MODEL_PATH = '../models/'
if MODEL_PATH not in sys.path:
sys.path.append(MODEL_PATH)
COMMON_PATH = '../common/'
if COMMON_PATH not in sys.path:
sys.path.append(COMMON_PATH)
from io_utils import read_text
from jupyter_utils import display_image_batch
from eval_tools import draw_match, draw_keypoints
MY_UTILS_PATH = '../../dnnutils/'
if MY_UTILS_PATH not in sys.path:
sys.path.append(MY_UTILS_PATH)
from book_plots import figsize
from jupyter_utils import display_image_batch
import tfvisualizer as tv
from tfvisualizer import log_images, convert_tile_image
from io_utils import load_pickle, read_text
from book_format import load_style
from det_tools import *
from spatial_transformer import transformer_crop, inplane_inverse_warp, inplane_coordinate_warp
load_style()`
to
`LOCAL_PATH = ''
if LOCAL_PATH not in sys.path:
sys.path.append(LOCAL_PATH)
from common.tf_layer_utils import *
from datasets import *
from det_tools import *
from inference import *
MODEL_PATH = 'models/'
if MODEL_PATH not in sys.path:
sys.path.append(MODEL_PATH)
COMMON_PATH = 'common/'
if COMMON_PATH not in sys.path:
sys.path.append(COMMON_PATH)
from io_utils import read_text
from jupyter_utils import display_image_batch
from eval_tools import draw_match, draw_keypoints
MY_UTILS_PATH = '../dnnutils/'
if MY_UTILS_PATH not in sys.path:
sys.path.append(MY_UTILS_PATH)
from book_plots import figsize
from jupyter_utils import display_image_batch
import tfvisualizer as tv
from tfvisualizer import log_images, convert_tile_image
from io_utils import load_pickle, read_text
from book_format import load_style
from det_tools import *
from spatial_transformer import transformer_crop, inplane_inverse_warp, inplane_coordinate_warp
load_style()`
Change cell 5 accordingly. It will be fine.
from lf-net-release.
Related Issues (20)
- Matching Score of SIFT on HPatches differs from SuperPoint HOT 1
- Find Matches HOT 11
- Training Pipeline HOT 7
- Invalid argument error HOT 2
- Evaluate on HPatches benchmark HOT 1
- Top K pixels gradient backpropagation HOT 3
- Using lf-net in OpenCV dnn HOT 4
- No file is found under the directory "/home" HOT 3
- What are the thetas and inv_thetas of next batch? HOT 3
- raise ValueError('Miss finding argument: unparsed={}\n'.format(unparsed)) HOT 1
- Inference time for images HOT 3
- Will you release a pytorch version? HOT 1
- A little problem with a function"logarithm_so3"? HOT 1
- description match HOT 9
- test datasets keypoints number HOT 1
- inverse_warp_view_2_to_1 HOT 1
- Return also the keypoint scores
- Find matches HOT 13
- Test on Roxford5k benchmark HOT 1
- where is the function 'euclidean_augmentation' in train_lfnet from? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lf-net-release.