Comments (6)
Thank you!
The aP calculation you have observed is not an error.
yolov3.weight is trained on the same coco dataset (by the author) but uses the different train/val split.
darknet
train : trainvalno5k
val : 5k
that can be obtained from:
https://github.com/pjreddie/darknet/blob/master/scripts/get_coco_dataset.sh#L22-L23
Ours
train : train2017
val : val2017
that can be obtained from:
http://cocodataset.org/#download
Because there is overlap between trainvalno5k and val2017, the aP calculation result using yolov3.weight on val2017 is higher than the reported one.
from pytorch_yolov3.
@hirotomusiker
Thanks a lot!
Using yolov3.weight on 5k, the mAP[IOU=0.5] is 0.547.
from pytorch_yolov3.
thanks a lot~
from pytorch_yolov3.
@TakashiNinjouji Hi! Do you know where can i find the json file of 5k.txt?
from pytorch_yolov3.
Hi,
you have to convert 5k.txt to json format.
datadir
is the path of the directory where you have 5k.txt, instances_train2017.json and instances_val2017.json.
- Load image ids from 5k.txt
import json
with open(datadir + "5k.txt", "r") as f:
txt_5k = f.read()
txt_5k = txt_5k.split('\n')
ids_5k = [int(w.split('_')[-1].split('.')[0]) for w in txt_5k[:-1]]
- extract annotations and image information from train2017 and val2017
train = json.load(open(datadir + "/instances_train2017.json"))
val = json.load(open(datadir + "/instances_val2017.json"))
images_ids = []
annot_ids = []
for an in train['annotations']:
if an['image_id'] in ids_5k:
annot_ids.append(an)
for im in train['images']:
if im['id'] in ids_5k:
images_ids.append(im)
for an in val['annotations']:
if an['image_id'] in ids_5k:
annot_ids.append(an)
for im in val['images']:
if im['id'] in ids_5k:
images_ids.append(im)
- save val5k file
val['images'] = images_ids
val['annotations'] = annot_ids
json.dump(val, open(datadir + "/instances_val5k.json", "w"))
Hope it will work for you 😃
from pytorch_yolov3.
Perfect!
thank you!
from pytorch_yolov3.
Related Issues (20)
- Hi, I simply copy your code and run,but i will also meet this problem.i changed the bctchsize to 8 when training in the visdrone dataset,
- problem about NMS in the evaluation.
- Error when training yolo on my dataset:IndexError: index 69 is out of bounds for dimension 3 with size 68 HOT 4
- how much time do you cost for training with pretrained model? and what the GPU you used? HOT 2
- Issues about the bboxes_iou
- class YOLOV3 forward function return error when using costumed data HOT 1
- Learning rate is low. HOT 1
- zero AP HOT 1
- The evaluation process is too slow!!! HOT 11
- Difference between .ckpt and .pt files HOT 1
- confused about the train loss、size_average and the performance. HOT 6
- Scale gain for loss HOT 2
- IMPORTANT: PyTorch_YOLOv3 will no longer be maintained from April 2020
- multy GPU support? HOT 1
- What is the FPS(testing speed)? HOT 3
- Low confidence score with high average precision
- Is my code for [sorting the clusters according to areas] and [matching clusters with ANCH_MASK] right?
- Why BCELoss for xy? HOT 2
- How to train custom dataset?
- On License
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.