Comments (7)
hi,
if phase not in ['train', 'test'], it should run this following lines
list_transforms = []
list_transforms.extend([ albu.Normalize(mean=(0.485, 0.456, 0.406),std=(0.229, 0.224, 0.225), p=1), ToTensor() ])
albu.Compose(list_transforms, bbox_params=albu.BboxParams(format='pascal_voc', min_area=min_area, min_visibility=min_visibility, label_fields=['category_id']))
from efficientdet.pytorch.
I meet the same question, and I have printed out all the feature map sizes. The problem I think is miss of resizing the input image. I also don't know the solution, and I change the 'valid' to 'train' and 'test' and find that the mAp is very low(13% for train and 0.6% for test). Is there any solution to the problem we have met?
from efficientdet.pytorch.
hi,
if phase not in ['train', 'test'], it should run this following lines
list_transforms = []
list_transforms.extend([ albu.Normalize(mean=(0.485, 0.456, 0.406),std=(0.229, 0.224, 0.225), p=1), ToTensor() ])
albu.Compose(list_transforms, bbox_params=albu.BboxParams(format='pascal_voc', min_area=min_area, min_visibility=min_visibility, label_fields=['category_id']))
yes, but it throws a runtimeerror... I think maybe I should resize the images and then feed them to the net, just like the 'test' mode does.
from efficientdet.pytorch.
from efficientdet.pytorch.
I meet the same question, and I have printed out all the feature map sizes. The problem I think is miss of resizing the input image. I also don't know the solution, and I change the 'valid' to 'train' and 'test' and find that the mAp is very low(13% for train and 0.6% for test). Is there any solution to the problem we have met?
HIi, I have met the same problem as yours, now, i run eval.py, map = 0.05, and some classes map is 0.
have you solved this problem? thanks.
from efficientdet.pytorch.
I also meet the same question, in validating , i changed the valid to 'test', and so, i get the mAp is 0.197 on VOC2012 Val.
The model was trained 187 epoches on Voc0712
last cls_loss : 0.1580013930797577
last reg_loss : 0.22156712412834167
last mean_loss : 0.5689369416236878
Can anybody help me ? thanks
from efficientdet.pytorch.
I meet the same question, and I have printed out all the feature map sizes. The problem I think is miss of resizing the input image. I also don't know the solution, and I change the 'valid' to 'train' and 'test' and find that the mAp is very low(13% for train and 0.6% for test). Is there any solution to the problem we have met?
HIi, I have met the same problem as yours, now, i run eval.py, map = 0.05, and some classes map is 0.
have you solved this problem? thanks.
hi, have you solved the question? thanks
from efficientdet.pytorch.
Related Issues (20)
- Training results in detections at all anchorboxes
- When I trained the code on my dataset, the mAP always kept 0.0. HOT 3
- zero confidence value
- is it possible to port official weights to your repo? HOT 1
- No boxes to NMS
- Can anyone train coco from scratch? HOT 1
- CUDA Out of Memory. The RTX 2080 TI 8GB can only afford the efficientdet-d3 with batch size 2. Why?
- 已经解决了win10下关于pytorch-EfficientDet下训练自己数据集的问题 HOT 2
- First time training, HTTP Error 403: Forbidden?! HOT 5
- threshold/iou_threshold
- KeyError: 'effcientdet-d0' How to solve this error? HOT 1
- train my datasets , IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed HOT 1
- When is TorchScript planed? HOT 1
- urllib.error.HTTPError: HTTP Error 403: Forbidden HOT 2
- how many gpu and u guys using for batch 64?
- --multiprocessing-distributed --multiprocessing-distributed
- How to download checkpoint_VOC_efficientdet-d1_34.pth HOT 1
- Size mismatch problem.
- Gradient computation error HOT 2
- EfficientDet-D0(with weight) doesn't exist, can't be loaded.
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 efficientdet.pytorch.