Comments (4)
label file should be a .txt
file, as in the original VOC.
can you fix that and try again?
from frcnn-from-scratch-with-keras.
My apologies. I made a mistake with my xml_to_csv. He generates the first row with column prefix like filename,x1,y2...
E:\images\01.jpg ....
csv or txt that does matter. Work with both.
from frcnn-from-scratch-with-keras.
My label file is annotate.txt where the rows are like this drive/My Drive/Colab Notebooks/frcnn/dataset/1.jpg",251,161,598,335,pothole
When I run this command
!python 'drive/My Drive/Colab Notebooks/frcnn/frcnn-from-scratch-with-keras/train_rpn.py' --network resnet50 -o simple -p 'drive/My Drive/Colab Notebooks/frcnn/dataset/annotate.txt'
I get this error
Parsing annotation files
Traceback (most recent call last):
File "drive/My Drive/Colab Notebooks/frcnn/frcnn-from-scratch-with-keras/train_rpn.py", line 130, in
all_imgs, classes_count, class_mapping = get_data(options.train_path)
File "/content/drive/My Drive/Colab Notebooks/frcnn/frcnn-from-scratch-with-keras/keras_frcnn/simple_parser.py", line 37, in get_data
(rows,cols) = img.shape[:2]
AttributeError: 'NoneType' object has no attribute 'shape'
I tried different solutions but I am unable to resolve
from frcnn-from-scratch-with-keras.
I m also facing the same issue.
get_data not able to read images from path. therefore attribute error..
any solution to that...
from frcnn-from-scratch-with-keras.
Related Issues (20)
- Why is the epoch_length is choosen as 1000? when should we change this? HOT 1
- Problem with AttributeError: 'str' object has no attribute 'shape' HOT 2
- Error during testing
- RPN is not producing bounding boxes that overlap the ground truth boxes. Check RPN settings or keep training.
- Anchor box generation when calculating the rpn HOT 1
- Unable to reproduce performance with PASCALVOC2010 and backbone resnet
- AttributeError: module 'tensorflow' has no attribute 'ConfigProto', how can I fix it ? HOT 1
- SystemExit: 2
- Can't train RPN separately (train_rpn.py)
- classifier_layers not used in resnet.py HOT 2
- RPN weights are not saved HOT 2
- How to write the results from the test_frcnn to a CSV file?
- Attempting to fetch value instead of handling error Internal: no supported devices found for platform CUDA
- Keyerror using measure_map for custom data using the trained VGG16 model
- Write the values of the predicted bounding boxes in measure_map
- How to plot feature maps from RPN model? HOT 1
- Cross Validation HOT 1
- Fit automated method instead of manually write it.
- Modify Network for Multi-task Learning
- ModuleNotFoundError: No module named 'tensorflow.compat.v1' HOT 1
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 frcnn-from-scratch-with-keras.