Comments (3)
log after 10 epech:
+-------+-------------+---------+
| Index | Class | AP |
+-------+-------------+---------+
| 0 | aeroplane | 0.00000 |
| 1 | bicycle | 0.00000 |
| 2 | bird | 0.00000 |
| 3 | boat | 0.00000 |
| 4 | bottle | 0.00000 |
| 5 | bus | 0.00000 |
| 6 | car | 0.00000 |
| 7 | cat | 0.00000 |
| 8 | chair | 0.00000 |
| 9 | cow | 0.00000 |
| 10 | diningtable | 0.00000 |
| 11 | dog | 0.00000 |
| 12 | horse | 0.00000 |
| 13 | motorbike | 0.00000 |
| 14 | person | 0.00000 |
| 15 | pottedplant | 0.00000 |
| 16 | sheep | 0.00000 |
| 17 | sofa | 0.00000 |
| 18 | train | 0.00000 |
| 19 | tvmonitor | 0.00000 |
+-------+-------------+---------+
---- mAP 0.00000 ----
from pytorch-yolov3.
from pytorch-yolov3.
I think I found a possible reason.
I read the function ‘compute_loss’ carefully, which describes the loss as:
Find the anchor that ground truth is responsible for in the three feature maps, and the bbox predicted by these responsible anchors are the positive examples. The authors consider the rest of the prediction bbox to be negative examples. Positive examples produce three-part losses for classification, confidence, and bbox regression. Negative examples produce only a loss of confidence. In calculating the loss of confidence, the positive examples are labelled with IoU of ground truth, while the negative examples are labelled with 0.
The problem is that there is a great imbalance between the positive and negative examples, and the calculation of the loss function does not seem to be consistent with what seems to be described in the paper. During my training, the network tends to output boxes with confidence 0, and the confidence of the prediction quickly turns negative after a few batches (it goes to 0 later after sigmod).
I'm a newcomer to the field of target detection. The above is just my personal understanding, there may be deviations in the understanding of the details of calculating the loss function in the code or the paper, welcome to discuss.
from pytorch-yolov3.
Related Issues (20)
- Replace own `Mish` implementation by torch's HOT 5
- Crash after processing JSON to RDF HOT 2
- Need help with getting bboxes.
- very low mAP on coco val2014 when training from scratch HOT 18
- how to set custom path for labels? please help me HOT 6
- how to adjust learning rates or something to be better when using a pretrained model to train my dataset?please give me some advice HOT 5
- i'm using yolov3.weights to test data/sample/, i found there are some wrong bboxes which are different from this projects HOT 8
- Unable to fully load data classes of classes.names HOT 1
- Questions regarding the evaluation model in train.py and test.py HOT 1
- PyTorch-YOLOv3 Tracking
- is woring in 3090,lower fps! HOT 2
- for Linux?or for windows? HOT 6
- Testing Suite
- 关于pytorchyolo1.8.0和GPU不兼容的问题 HOT 1
- 怎么把pytorchyolo卸载干净呀? HOT 2
- how can i calculate the params and flops of yolov3-tiny model 如何计算 yolov3-tiny 模型的参数和计算量?
- Would support torchv2.2.2?
- tensorboard没有显示的结果? HOT 1
- How to compute FPS
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 pytorch-yolov3.