Comments (9)
it would be appreciated if you give some advise on this issue
from keras-yolov3-mobilenet.
Can you detect anything in the testset?if not,what is your learning rate,lr decay pacience?
from keras-yolov3-mobilenet.
I am sorry, it seems to my mistakes.
the first training is to get a stable loss
the second training without frozen layers is to get a lower loss?
from keras-yolov3-mobilenet.
correct
from keras-yolov3-mobilenet.
I got a lower loss than 40, but it still is 38
the result in my testdset looks ok, i do not konw how to decrease the loss
from keras-yolov3-mobilenet.
@guapizyq @Adamdad I am very happy to discuss with you. What I want to ask is, 1. How much is the epoch setting of the red arrow here? 2, how much is the initial_epoch setting of the two black arrows? I look forward to your answer.
from keras-yolov3-mobilenet.
And why is it divided into step-by-step training?the first training? the second training ?What is their role?
from keras-yolov3-mobilenet.
The first training part is for finetuning a model quickly. It freezes most layers, only to train on the last few layers. We can get an acceptable model for detection in a short period of time
The second training part is for getting a complete model. All the layers can be trained through this process.
Under most occasions, I only use the second part. Epoch under is not important here.
from keras-yolov3-mobilenet.
The first training part is for finetuning a model quickly. It freezes most layers, only to train on the last few layers. We can get an acceptable model for detection in a short period of time
The second training part is for getting a complete model. All the layers can be trained through this process.
Under most occasions, I only use the second part. Epoch under is not important here.
After model training, I have a model with size of 277M. It is bigger than YOLO-v3,Why?
Doesn't MobileNet reduce model parameters?
This is my training strategy in my dateset.
- Unfreeze all of the layers
- learning_rate = 0.001
- load_pretrained=False
- batch_size = 16
from keras-yolov3-mobilenet.
Related Issues (20)
- Convert Darknet conv-lstm to .h5
- Training and Validation Loss HOT 4
- about vgg16 of the baseNet?
- convert .h5 to .pb HOT 3
- problem of .h5 to .pb
- What should I do to train model with 1080p images
- How to setting to use GPU?
- KeyError: 'val_loss' HOT 1
- Highly doubt your result!? HOT 2
- mobilenet = MobileNet(input_tensor=inputs,weights='imagenet')
- 你不觉得kmean出来的avg_iou很低吗?只有10几
- Nice job. But why is the avg_iou from kmeans.py so small(10%)?
- widerface training
- Missing: calculation of bounding box center relative to grid cell in `preprocess_true_boxes`
- AttributeError: 'list' object has no attribute 'show'
- Error During training on Custom Dataset HOT 1
- How to deploy this model to android
- Example of tain_path and val_path HOT 1
- I want to know if this project is using mobilenetv1? HOT 1
- For custom model
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-yolov3-mobilenet.