Comments (6)
I've got the pretrained model from google drive,
but I now can't figure out how to actually run them.
What parts of codes should I modify , and what command lines should I use to run them?Can you kindly share the Google Drive link to the pre-trained model.
https://drive.google.com/drive/folders/1Y1cGm-sRO0VMSHnDqfmIWA_hl-2fqPWn
from csp.
I've got the pretrained model from google drive,
but I now can't figure out how to actually run them.
What parts of codes should I modify , and what command lines should I use to run them?
hi, have you run the pretrained model?
Can you tell me how to run the pretrained model?
from csp.
I've got the pretrained model from google drive,
but I now can't figure out how to actually run them.
What parts of codes should I modify , and what command lines should I use to run them?
Can you kindly share the Google Drive link to the pre-trained model.
from csp.
From test_caltech.py, change some lines.
#if not os.path.exists(out_path):
#os.makedirs(out_path)
#files = sorted(os.listdir(w_path)) # get each files in w_path + sorting
#for w_ind in range(51, 121): # get files from epoch 51 to 120
#for f in files:
#if f.split('')[0] == 'net' and int(f.split('')[1][1:]) == w_ind: # if net epoch 51~120
#break
cur_file = 'net_e82_l0.00850005054218.hdf5' # pretrained from citypersons
weight1 = os.path.join(w_path, cur_file) # pathname + file name
print 'load weights from {}'.format(weight1)
model.load_weights(weight1, by_name=True) # get weight from trained models
res_path = os.path.join(out_path, '082+city') #result path = valresults/caltech/h/off/065 ###
from csp.
Also I have changed the score from 0.01 to 0.5 following #38
boxes = bbox_process.parse_det_offset(Y, C, score=0.5,down=4) # originally 0.01
from csp.
Also I have changed the score from 0.01 to 0.5 following #38
boxes = bbox_process.parse_det_offset(Y, C, score=0.5,down=4) # originally 0.01
Excuse me, I have made the codes work and tested my images. But the output of 'Y' is a tensor close to zero. Could you give me some advice? Thanks.
Y = model.predict(x_rcnn)
from csp.
Related Issues (20)
- The losses value from train_Caltech are higher than authors
- I have data and need to test my data with this pre-trained model
- An exception occurs when running train_caltech
- How to generate heat map
- No module named 'nms_wrapper' HOT 1
- windows user how to test caltech? HOT 2
- Is nms postprocess necessary?
- How to run test_wider_ms.py with multiple GPUs
- Python version of dt_txt2json HOT 2
- How to generate the cache file of test subset in wider face?
- Share the code of how to execute the multi-scale training for the citypersons dataset?
- Classification loss - binary_crossentropy (possibly wrong parameters order) HOT 1
- batchsize 16 on one 2080ti cause OOM exception
- it shows me that Dimensions is not equal HOT 2
- where val dataset? i just see the train
- how to run this github
- Does anyone reproduce the caltech result using author's weight?
- how can I get the image with the bounding boxes like this HOT 2
- why the classification is a binary classification? in the cityperson dataset , it have 6 class pedestrian ?
- ImportError: Building module keras_csp.nms.gpu_nms failed: ["distutils.errors.CompileError: command 'gcc' failed with exit status 1\n"]
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 csp.