Comments (12)
@mkvashennikov I haven't looked a this since 2019. I don't remember fixing it. I think I used another implementation.
from keras-fasterrcnn.
I've also been facing the same problem, maybe the dataset is too small and the code is incapable of transfer learning
from keras-fasterrcnn.
i use the voc2012, i've also been facing the same problem.
from keras-fasterrcnn.
I went into checking the code of this file; found out that the bboxes dict is empty, thereafter, running a for loop on it will be nullified (which contains the bbox plotting). I guess reducing bbox threshold may fix it, tho I haven't tried it yet.
from keras-fasterrcnn.
I train VOC2012 epochs=126 loss rpn classifier = 3.22 oscillate around 3 without falling.
from keras-fasterrcnn.
Maybe the data set is too big? Or is there a problem with the parameters of the training?
from keras-fasterrcnn.
My model is currently only able to detect people and train for 8 hours. The current box is not very accurate
from keras-fasterrcnn.
Dataset is of 3471 images (originally of 267 images, increased by augmentation). Parameters of training are as default except I changed the learning rate to 0.01, and others optimizers, but same result.
from keras-fasterrcnn.
@3ST4R I have tested this and it seems even if the bbox threshold is set to zero there still is no bbox.
from keras-fasterrcnn.
@collinarnett I also checked your post about weights not loading, and I tried that, still there is no bbox.
So, what should be a possible solution to this problem. As, I see the blogs where people getting it working absolutely fine, without any digging into the code, I wonder how.
from keras-fasterrcnn.
@3ST4R have u fixed this problem? I'm facing this problem too.
from keras-fasterrcnn.
I train VOC2012 epochs=126 loss rpn classifier = 3.22 oscillate around 3 without falling.
@3ST4R, @collinarnett im facing with this problem too. Maybe you fix this problem..?
from keras-fasterrcnn.
Related Issues (20)
- tensorflow.python.framework.errors_impl.InvalidArgumentError: slice index 14 of dimension 1 out of bounds. HOT 2
- Train Model Fail
- It doesn't train,Epoch 1/2000,and stop for one hour HOT 2
- How does val_loss works when train model
- How should I run the inference?
- Can anyone pls explain this region of code? Why are we only taking num_regions/2 positive and negative boxes?
- Pre-train for inception resnet v2 HOT 1
- Data Augmentation
- Plot the model
- Incompatible shapes
- custom dataset
- tf2 - from colab to local machine - problems with TimeDistributed
- stuck at epoch 1 for vgg HOT 1
- trained hdf5 file
- Unable to reproduce PASCAL VOC performance
- Exception: 'a' cannot be empty unless no samples are taken
- How to check Testing accuracy
- AttributeError: 'Node' object has no attribute 'output_masks' HOT 1
- ValueError: Attempt to convert a value (None) with an unsupported type (<class 'NoneType'>) to a Tensor. HOT 1
- Parallel Computing
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 keras-fasterrcnn.