Comments (1)
Please add this function in the utils.py:
def read_pred_and_gt(pred_file,gt_file):
# read pred
pred_data = {}
with open(pred_file) as f:
id_read = []
for line in f.readlines():
line = line.strip().split(' ')
# check1
if len(line) <2 or len(line) % 2 !=0 or (len(line)-2)/2 != int(line[1]):
flagError = True
sys.exit(1)
line_data = [int(i) for i in line]
idx, num = [line_data[0], line_data[1]]
id_read.append(idx)
points = []
if num>0:
points = np.array(line_data[2:]).reshape(((len(line)-2)//2,2))
pred_data[idx] = {'num': num, 'points':points}
else:
pred_data[idx] = {'num': num, 'points':[]}
# read gt
gt_data = {}
with open(gt_file) as f:
for line in f.readlines():
line = line.strip().split(' ')
line_data = [int(i) for i in line]
idx, num = [line_data[0], line_data[1]]
points_r = []
if num>0:
points_r = np.array(line_data[2:]).reshape(((len(line)-2)//5,5))
gt_data[idx] = {'num': num, 'points':points_r[:,0:2], 'sigma': points_r[:,2:4], 'level':points_r[:,4]}
else:
gt_data[idx] = {'num': 0, 'points':[], 'sigma':[], 'level':[]}
return pred_data, gt_data
In addition, we have updated the code. Thanks for your feedback!
from iim.
Related Issues (20)
- 模型在哪里?怎样测试一张图片,得到人数?
- val_gt_loc.txt is used only in the test time.
- OOM
- killed when self.validate() HOT 1
- 数据集
- 下载
- 运行vis4val.py时出错 Key Error 求解~ HOT 1
- net.load_state_dict(new_state_dict,False) HOT 1
- 关于源码里面BinarizedF的反传部分的疑惑 HOT 2
- loss不是很懂 HOT 6
- 我在training時遇到以下錯誤 HOT 1
- 训练时有足够内存,依然得到out of memory问题 HOT 1
- 训练时有足够得内存,依然得到out of memory问题
- 模型保存为pt时报错RuntimeError: Could not export Python function call 'BinarizedF' HOT 1
- Great work but Threshold Encoder module is useless.Details look at the picture HOT 3
- How to visualize other datasets test set pictures? HOT 7
- 怎样转化为onnx模型 HOT 3
- threshold appear to be nan during the training process HOT 2
- RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. HOT 1
- How to config to train on NVIDIA GeForce RTX 3090 Ti/PCIe/SSE2 HOT 6
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 iim.