PSMNet debug(七)

submission.py

       imgL = processed(imgL_o).numpy()
       imgR = processed(imgR_o).numpy()
       print('processed imgL')
       print('imgL size0=%d' %(imgL.shape[0]))
       print('imgL size1=%d' %(imgL.shape[1]))
       print('imgL size2=%d' %(imgL.shape[2]))

       imgL = np.reshape(imgL,[1,3,imgL.shape[1],imgL.shape[2]])
       imgR = np.reshape(imgR,[1,3,imgR.shape[1],imgR.shape[2]])
       print('reshape imgL')
       print('imgL size0=%d' %(imgL.shape[0]))
       print('imgL size1=%d' %(imgL.shape[1]))
       print('imgL size2=%d' %(imgL.shape[2]))
       print('imgL size3=%d' %(imgL.shape[3]))

       # pad to (384, 1248) 540
       top_pad = 384-imgL.shape[2]#384 768
       left_pad = 1248-imgL.shape[3]
       imgL = np.lib.pad(imgL,((0,0),(0,0),(top_pad,0),(0,left_pad)),mode='constant',constant_values=0)
       imgR = np.lib.pad(imgR,((0,0),(0,0),(top_pad,0),(0,left_pad)),mode='constant',constant_values=0)

       start_time = time.time()
     
       print('reshape imgL')
       print('imgL size0=%d' %(imgL.shape[0]))
       print('imgL size1=%d' %(imgL.shape[1]))
       print('imgL size2=%d' %(imgL.shape[2]))
       print('imgL size3=%d' %(imgL.shape[3]))

 

打印结果：

processed imgL
imgL size0=3
imgL size1=375
imgL size2=1242

reshape imgL
imgL size0=1
imgL size1=3
imgL size2=375
imgL size3=1242

reshape imgL
imgL size0=1
imgL size1=3
imgL size2=384
imgL size3=1248