Changing "voc0712"in demo.py model = SSD300( to 'watercolor_dt_ssd300'

[Twenkid]

In order to run one of the demos I found that a line in demo.py had to be changed from voc0712 to the name of the model I used: watercolor_dt_ssd300.

model = SSD300(
n_fg_class=len(voc_bbox_label_names), pretrained_model='watercolor_dt_ssd300') #voc0712')

It produced a correct box. With the original voc0712 it was failing to load voc0712 (I don't know why it has to since an URL is given), I guess the server is not working anymore:

Downloading ...
From: https://chainercv-models.preferred.jp/ssd300_voc0712_converted_2017_06_06.npz
To: /root/.chainer/dataset/_dl_cache/7580b6888d3f7742a1b531234009c0b0
Traceback (most recent call last):
  File "/usr/lib/python3.10/urllib/request.py", line 1348, in do_open
    h.request(req.get_method(), req.selector, req.data, headers,
  File "/usr/lib/python3.10/http/client.py", line 1283, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "/usr/lib/python3.10/http/client.py", line 1329, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "/usr/lib/python3.10/http/client.py", line 1278, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "/usr/lib/python3.10/http/client.py", line 1038, in _send_output
    self.send(msg)
  File "/usr/lib/python3.10/http/client.py", line 976, in send
    self.connect()
  File "/usr/lib/python3.10/http/client.py", line 1448, in connect
    super().connect()
  File "/usr/lib/python3.10/http/client.py", line 942, in connect
    self.sock = self._create_connection(
  File "/usr/lib/python3.10/socket.py", line 824, in create_connection
    for res in getaddrinfo(host, port, 0, SOCK_STREAM):
  File "/usr/lib/python3.10/socket.py", line 955, in getaddrinfo
    for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
socket.gaierror: [Errno -2] Name or service not known

python demo.py input/watercolor_142090457.jpg output.jpg --gpu 0 --load models/watercolor_dt_pl_ssd300

(I actually used it without --gpu on a CPU session in Colab)

However with dt_ssd300:
python demo.py input/watercolor_142090457.jpg output.jpg --gpu 0 --load models/watercolor_dt_ssd300

Now that I read the whole readme.md, I see that pl stands for pseudo labeling, I don't know is it a problem and haven't tried the right way, that could be another session.

https://github.com/Twenkid/cross-domain-detection

[Twenkid]

I created a pull request with a required --load (but not tested for typos)
#47