Comments (2)
from pytorch-faster-rcnn.
Hello, I meet a question that the loss decline too fast as follows. I use the resnet50_fpn as my backbone. I want to ask that whether you meet this question or not. Looking forward to your reply, thanks.
Epoch: [0] [ 0/824] eta: 1:19:37.181170 lr: 0.000500 loss: 1.4562 (1.4562) loss_classifier: 0.7254 (0.7254) loss_box_reg: 0.0033 (0.0033) loss_objectness: 0.7002 (0.7002) loss_rpn_box_reg: 0.0274 (0.0274) time: 5.7976 data: 3.9277 max mem: 4177
Epoch: [0] [ 50/824] eta: 0:11:35.486613 lr: 0.000500 loss: 0.1906 (0.5048) loss_classifier: 0.0321 (0.1367) loss_box_reg: 0.0104 (0.0084) loss_objectness: 0.1034 (0.3157) loss_rpn_box_reg: 0.0383 (0.0440) time: 0.7947 data: 0.0023 max mem: 4177
Epoch: [0] [100/824] eta: 0:10:16.592875 lr: 0.000500 loss: 0.2026 (0.3515) loss_classifier: 0.0584 (0.0951) loss_box_reg: 0.0380 (0.0189) loss_objectness: 0.0676 (0.1965) loss_rpn_box_reg: 0.0309 (0.0410) time: 0.8105 data: 0.0022 max mem: 4177
Epoch: [0] [150/824] eta: 0:09:23.404139 lr: 0.000500 loss: 0.2181 (0.3054) loss_classifier: 0.0638 (0.0837) loss_box_reg: 0.0624 (0.0301) loss_objectness: 0.0614 (0.1540) loss_rpn_box_reg: 0.0256 (0.0376) time: 0.8020 data: 0.0022 max mem: 4177
from pytorch-faster-rcnn.
Related Issues (20)
- you got my star
- wrong out features on cls_logits
- rel_codes can not reshape bug
- AttributeError: module 'torch.distributed' has no attribute 'barrier' HOT 2
- Model parameter error HOT 1
- i think anchor has error
- Question about CPU use HOT 3
- Error using resnet50-fpn backbone HOT 2
- Please help me HOT 1
- Default process group has not been initialized, please make sure to call init_process_group HOT 4
- FPN101 error
- Need for Pretrained weights with vgg16 and HRNet
- thanks for your contribution ,still lack some code.look for your message HOT 1
- How to run the code on pytorch1.7 Nvidia 3090? HOT 4
- When I install HOT 1
- Question about the Result HOT 5
- I want to know how much mAP can this method get? HOT 1
- RuntimeError: shape '[516096, -1]' is invalid for input of size 2095104 HOT 3
- can we train this using multiple gpu, let's say a single machine with 4 gpus.
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-faster-rcnn.