how to train model on vl_cmu_cd dataset?

[jcluo1994]

thanks for sharing your great work.when i use this code train my model like vl_cmu_cd format,but it did't work,the error is the following:
return _VF.broadcast_tensors(tensors) # type: ignore[attr-defined]
RuntimeError: The size of tensor a (512) must match the size of tensor b (3) at non-singleton dimension 4
look forward for your reply

[wangle53]

This problem is about the input tensor shape of the ground truth. Please confirm your input gt's shape.

[wangle53]

The gt's shape should be (B 1 H W).

[jcluo1994]

The gt's shape should be (B 1 H W).

thanks for reply,which format of vl_cmu_cd dataset should be selected ,the gt**.png or maks**.png?

[wangle53]

Please covert the gt.png in vl_cmu_cd dataset into mask.png which denotes the change map.

[jcluo1994]

Please covert the gt.png in vl_cmu_cd dataset into mask.png which denotes the change map.
that means consisting of two labels (change and no-change)for change detection,ok i will try again.

[wangle53]

It seems vlcmucd only has semantic labels instead of CD labels. You need to generate CD labels before training. Please review it's introduction in their paper.

[jcluo1994]

It seems vlcmucd only has semantic labels instead of CD labels. You need to generate CD labels before training. Please review it's introduction in their paper.

yes, i have convert the dataset to binary,and, the code is running.but, the new error is the following:

Traceback (most recent call last):
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connection.py", line 175, in _new_conn
(self._dns_host, self.port), self.timeout, **extra_kw
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/util/connection.py", line 95, in create_connection
raise err
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/util/connection.py", line 85, in create_connection
sock.connect(sa)
ConnectionRefusedError: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connectionpool.py", line 710, in urlopen
chunked=chunked,
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/http/client.py", line 1287, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/http/client.py", line 1333, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/http/client.py", line 1282, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/http/client.py", line 1042, in _send_output
self.send(msg)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/http/client.py", line 980, in send
self.connect()
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connection.py", line 205, in connect
conn = self._new_conn()
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connection.py", line 187, in _new_conn
self, "Failed to establish a new connection: %s" % e
urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x7fd559f9c710>: Failed to establish a new connection: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/requests/adapters.py", line 450, in send
timeout=timeout
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connectionpool.py", line 788, in urlopen
method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2]
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/util/retry.py", line 592, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /events (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fd559f9c710>: Failed to establish a new connection: [Errno 111] Connection refused',))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/visdom/init.py", line 695, in _send
data=json.dumps(msg),
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/visdom/init.py", line 656, in _handle_post
r = self.session.post(url, data=data)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/requests/sessions.py", line 577, in post
return self.request('POST', url, data=data, json=json, **kwargs)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/requests/sessions.py", line 529, in request
resp = self.send(prep, **send_kwargs)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/requests/sessions.py", line 645, in send
r = adapter.send(request, **kwargs)
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/requests/adapters.py", line 519, in send
raise ConnectionError(e, request=request)
requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /events (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fd559f9c710>: Failed to establish a new connection: [Errno 111] Connection refused',))
Traceback (most recent call last):
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/connection.py", line 175, in _new_conn
(self._dns_host, self.port), self.timeout, **extra_kw
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/util/connection.py", line 95, in create_connection
raise err
File "/home/inspur/anaconda3/envs/pytorch/lib/python3.6/site-packages/urllib3/util/connection.py", line 85, in create_connection
sock.connect(sa)
ConnectionRefusedError: [Errno 111] Connection refused

[wangle53]

Did u open visdom?

[jcluo1994]

Thank you for your guidance.The code is already running.i use test.txt as val.txt in vl_cmu_cd dataset.but the value of f1 is always 0.

[wangle53]

Something must be wrong. You may carefully check your input and gt.Please make sure your the final input gt value is between 0 and 1.

[jcluo1994]

Something must be wrong. You may carefully check your input and gt.Please make sure your the final input gt value is between 0 and 1.

Thank you for your reply. There are 11 classes in the vl_cmu_cd dataset, which means that the label values are the eleven values of [0,1]. Is that right?

[wangle53]

No, you misunderstand what i mean. As shown in the follow img.

1. convert gt.png into binary CD labels mask.png.
2. Please make sure the input mask.png within the range of [0, 1].

[jcluo1994]

No, you misunderstand what i mean. As shown in the follow img.

1. convert gt.png into binary CD labels mask.png.
2. Please make sure the input mask.png within the range of [0, 1].

Yes, Sir. I see what you mean and I am revising it. I'll tell you the good news when I finish the work. Thank you very sincerely.

[wangle53]

You are welcome. Hope u will contact me again if u have further questions.

[jcluo1994]

You are welcome. Hope u will contact me again if u have further questions.

Good afternoon, the code is running correctly and I have read your code carefully again. There are some doubts. For example,config.category = ['test']，I don't know what that does. It didn't seem to work in the end.

I've highlighted the exact location in the picture.

[wangle53]

It seems this code are redundant. Please delete it.

[wangle53]

Thanks for ur reminding, I will update the code later.

[jcluo1994]

Thanks for ur reminding, I will update the code later.
I've learned a lot from your code, and config.category = ['test'] it works in test.py.I will continue to learn your code.

[wangle53]

I'm so glad that my work helps you. Good luck.

[jcluo1994]

I'm so glad that my work helps you. Good luck.

Hello, That's exciting news.I have developed my own model using open source data. It looks pretty good.However, I want to make my own data set, but I don't know how to set the label value of the data set. could you give me some guidance?

[wangle53]

The label values of semantic objects are all up to u. In a general way, for CD task, labels are set [0, 1] or [0, 255]. If u want to label ur own dataset like the setting in VL-CMU-CD, only give a specific value for each semantic category. The label tool is introduced to use 'labelme'.

[jcluo1994]

The label values of semantic objects are all up to u. In a general way, for CD task, labels are set [0, 1] or [0, 255]. If u want to label ur own dataset like the setting in VL-CMU-CD, only give a specific value for each semantic category. The label tool is introduced to use 'labelme'.

I think I know what you mean, just mark the difference, the corresponding name doesn't matter. In the figure below, I have marked the differences, using numbers instead of label names for simplicity. Finally, the pixel value of the image is converted to [0,1].

[wangle53]

It's ok.

[jcluo1994]

It's ok.

Ok, thank you for your guidance.

[jcluo1994]

long time no see, how are you lately? I am planning to do some changedetection projects recently, I would like to ask you, is there a relationship between the accuracy of detection and the depth of the network?

[jcluo1994]

long time no see, how are you lately? I am planning to do some changedetection projects recently, I would like to ask you, is there a relationship between the accuracy of detection and the depth of the network?

[wangle53]

Within limits，it is.

[jcluo1994]

ok, i got it.