CSP icon indicating copy to clipboard operation
CSP copied to clipboard

how to run pretrained model?

Open lookdeceline opened this issue 6 years ago • 6 comments

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?

lookdeceline avatar Jul 20 '19 05:07 lookdeceline

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?

globalmaster avatar Aug 02 '19 08:08 globalmaster

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.

AbdullahMakhdoom avatar Aug 05 '19 17:08 AbdullahMakhdoom

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 ###

bomtorazek avatar Aug 14 '19 18:08 bomtorazek

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

bomtorazek avatar Aug 14 '19 18:08 bomtorazek

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)

slypanzer avatar Oct 24 '19 13:10 slypanzer

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

M-Usman10 avatar Nov 15 '19 12:11 M-Usman10