joeking11829 / py-faster-rcnn-tk1

Other
2 stars 1 forks source link

py_faster not running #2

Open EDTejadaG opened 7 years ago

EDTejadaG commented 7 years ago

Hi, I am testing this version in the TK1, I manage to install caffe with cuDNN and everything is working. The problem is that when I run ./tools/demo.py It initializes the network but I get a warning and after a little while I get a "killed" message.:

[libprotobuf WARNING google/protobuf/io/coded_stream.cc:505] Reading dangerously large protocol message.  If the message turns out to be larger than 2147483647 bytes, parsing will be halted for security reasons.  To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 548317115

Loaded network /home/ubuntu/py-faster-rcnn-tk1/data/faster_rcnn_models/VGG16_faster_rcnn_final.caffemodel

Killed

After a couple of test I found that the demo is failing at the warmup part:

    im = 128 * np.ones((300, 500, 3), dtype=np.uint8)

    for i in xrange(2):
        _, _= im_detect(net, im)

Inside im_detect(), in the do forward part

# do forward
    forward_kwargs = {'data': blobs['data'].astype(np.float32, copy=False)}
    if cfg.TEST.HAS_RPN:
        forward_kwargs['im_info'] = blobs['im_info'].astype(np.float32, copy=False)
    else:
        forward_kwargs['rois'] = blobs['rois'].astype(np.float32, copy=False)
    blobs_out = net.forward(**forward_kwargs)

Specifically in net.forward()

I would like to know why that could be and to fix this problem.

Thanks for your help!

guoqiang01486 commented 6 years ago

l meet the same problem, do you solve the problem?