neurosys-pl / objects_counting_dmap Goto Github PK
View Code? Open in Web Editor NEWObjects counting from density map
License: Apache License 2.0
Objects counting from density map
License: Apache License 2.0
How I can run this part? Maybe I could be wrong...
This is what I am running:
% python infer.py -n UNet -c cell_FCRN_A.pth -i /Users/elena/Desktop/objects_counting_dmap-master/examples/example_cell.png --visualize
The error:
Traceback (most recent call last):
File "infer.py", line 128, in
infer()
File "/opt/anaconda3/lib/python3.8/site-packages/click/core.py", line 829, in call
return self.main(*args, **kwargs)
File "/opt/anaconda3/lib/python3.8/site-packages/click/core.py", line 782, in main
rv = self.invoke(ctx)
File "/opt/anaconda3/lib/python3.8/site-packages/click/core.py", line 1066, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/opt/anaconda3/lib/python3.8/site-packages/click/core.py", line 610, in invoke
return callback(*args, **kwargs)
File "infer.py", line 83, in infer
network.load_state_dict(torch.load(checkpoint.name))
File "/opt/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1497, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DataParallel:
Missing key(s) in state_dict: "module.block1.0.0.weight", "module.block1.0.1.weight", "module.block1.0.1.bias", "module.block1.0.1.running_mean", "module.block1.0.1.running_var", "module.block1.1.0.weight", "module.block1.1.1.weight", "module.block1.1.1.bias", "module.block1.1.1.running_mean", "module.block1.1.1.running_var", "module.block2.0.0.weight", "module.block2.0.1.weight", "module.block2.0.1.bias", "module.block2.0.1.running_mean", "module.block2.0.1.running_var", "module.block2.1.0.weight", "module.block2.1.1.weight", "module.block2.1.1.bias", "module.block2.1.1.running_mean", "module.block2.1.1.running_var", "module.block3.0.0.weight", "module.block3.0.1.weight", "module.block3.0.1.bias", "module.block3.0.1.running_mean", "module.block3.0.1.running_var", "module.block3.1.0.weight", "module.block3.1.1.weight", "module.block3.1.1.bias", "module.block3.1.1.running_mean", "module.block3.1.1.running_var", "module.block4.conv.0.0.0.weight", "module.block4.conv.0.0.1.weight", "module.block4.conv.0.0.1.bias", "module.block4.conv.0.0.1.running_mean", "module.block4.conv.0.0.1.running_var", "module.block4.conv.0.1.0.weight", "module.block4.conv.0.1.1.weight", "module.block4.conv.0.1.1.bias", "module.block4.conv.0.1.1.running_mean", "module.block4.conv.0.1.1.running_var", "module.block5.conv.0.0.0.weight", "module.block5.conv.0.0.1.weight", "module.block5.conv.0.0.1.bias", "module.block5.conv.0.0.1.running_mean", "module.block5.conv.0.0.1.running_var", "module.block5.conv.0.1.0.weight", "module.block5.conv.0.1.1.weight", "module.block5.conv.0.1.1.bias", "module.block5.conv.0.1.1.running_mean", "module.block5.conv.0.1.1.running_var", "module.block6.conv.0.0.0.weight", "module.block6.conv.0.0.1.weight", "module.block6.conv.0.0.1.bias", "module.block6.conv.0.0.1.running_mean", "module.block6.conv.0.0.1.running_var", "module.block6.conv.0.1.0.weight", "module.block6.conv.0.1.1.weight", "module.block6.conv.0.1.1.bias", "module.block6.conv.0.1.1.running_mean", "module.block6.conv.0.1.1.running_var", "module.block7.0.0.weight", "module.block7.0.1.weight", "module.block7.0.1.bias", "module.block7.0.1.running_mean", "module.block7.0.1.running_var", "module.block7.1.0.weight", "module.block7.1.1.weight", "module.block7.1.1.bias", "module.block7.1.1.running_mean", "module.block7.1.1.running_var", "module.density_pred.weight".
Unexpected key(s) in state_dict: "module.model.0.0.0.weight", "module.model.0.0.1.weight", "module.model.0.0.1.bias", "module.model.0.0.1.running_mean", "module.model.0.0.1.running_var", "module.model.0.0.1.num_batches_tracked", "module.model.0.1.0.weight", "module.model.0.1.1.weight", "module.model.0.1.1.bias", "module.model.0.1.1.running_mean", "module.model.0.1.1.running_var", "module.model.0.1.1.num_batches_tracked", "module.model.0.2.0.weight", "module.model.0.2.1.weight", "module.model.0.2.1.bias", "module.model.0.2.1.running_mean", "module.model.0.2.1.running_var", "module.model.0.2.1.num_batches_tracked", "module.model.2.0.0.weight", "module.model.2.0.1.weight", "module.model.2.0.1.bias", "module.model.2.0.1.running_mean", "module.model.2.0.1.running_var", "module.model.2.0.1.num_batches_tracked", "module.model.2.1.0.weight", "module.model.2.1.1.weight", "module.model.2.1.1.bias", "module.model.2.1.1.running_mean", "module.model.2.1.1.running_var", "module.model.2.1.1.num_batches_tracked", "module.model.2.2.0.weight", "module.model.2.2.1.weight", "module.model.2.2.1.bias", "module.model.2.2.1.running_mean", "module.model.2.2.1.running_var", "module.model.2.2.1.num_batches_tracked", "module.model.4.0.0.weight", "module.model.4.0.1.weight", "module.model.4.0.1.bias", "module.model.4.0.1.running_mean", "module.model.4.0.1.running_var", "module.model.4.0.1.num_batches_tracked", "module.model.4.1.0.weight", "module.model.4.1.1.weight", "module.model.4.1.1.bias", "module.model.4.1.1.running_mean", "module.model.4.1.1.running_var", "module.model.4.1.1.num_batches_tracked", "module.model.4.2.0.weight", "module.model.4.2.1.weight", "module.model.4.2.1.bias", "module.model.4.2.1.running_mean", "module.model.4.2.1.running_var", "module.model.4.2.1.num_batches_tracked", "module.model.6.0.0.weight", "module.model.6.0.1.weight", "module.model.6.0.1.bias", "module.model.6.0.1.running_mean", "module.model.6.0.1.running_var", "module.model.6.0.1.num_batches_tracked", "module.model.6.1.0.weight", "module.model.6.1.1.weight", "module.model.6.1.1.bias", "module.model.6.1.1.running_mean", "module.model.6.1.1.running_var", "module.model.6.1.1.num_batches_tracked", "module.model.6.2.0.weight", "module.model.6.2.1.weight", "module.model.6.2.1.bias", "module.model.6.2.1.running_mean", "module.model.6.2.1.running_var", "module.model.6.2.1.num_batches_tracked", "module.model.8.0.0.weight", "module.model.8.0.1.weight", "module.model.8.0.1.bias", "module.model.8.0.1.running_mean", "module.model.8.0.1.running_var", "module.model.8.0.1.num_batches_tracked", "module.model.8.1.0.weight", "module.model.8.1.1.weight", "module.model.8.1.1.bias", "module.model.8.1.1.running_mean", "module.model.8.1.1.running_var", "module.model.8.1.1.num_batches_tracked", "module.model.8.2.0.weight", "module.model.8.2.1.weight", "module.model.8.2.1.bias", "module.model.8.2.1.running_mean", "module.model.8.2.1.running_var", "module.model.8.2.1.num_batches_tracked", "module.model.10.0.0.weight", "module.model.10.0.1.weight", "module.model.10.0.1.bias", "module.model.10.0.1.running_mean", "module.model.10.0.1.running_var", "module.model.10.0.1.num_batches_tracked", "module.model.10.1.0.weight", "module.model.10.1.1.weight", "module.model.10.1.1.bias", "module.model.10.1.1.running_mean", "module.model.10.1.1.running_var", "module.model.10.1.1.num_batches_tracked", "module.model.10.2.0.weight", "module.model.10.2.1.weight", "module.model.10.2.1.bias", "module.model.10.2.1.running_mean", "module.model.10.2.1.running_var", "module.model.10.2.1.num_batches_tracked", "module.model.12.0.0.weight", "module.model.12.0.1.weight", "module.model.12.0.1.bias", "module.model.12.0.1.running_mean", "module.model.12.0.1.running_var", "module.model.12.0.1.num_batches_tracked", "module.model.12.1.0.weight", "module.model.12.1.1.weight", "module.model.12.1.1.bias", "module.model.12.1.1.running_mean", "module.model.12.1.1.running_var", "module.model.12.1.1.num_batches_tracked", "module.model.12.2.0.weight", "module.model.12.2.1.weight", "module.model.12.2.1.bias", "module.model.12.2.1.running_mean", "module.model.12.2.1.running_var", "module.model.12.2.1.num_batches_tracked".
Hi!
Ifind you're work interesting, I'd like to test it. I have downloaded mall dataset with your get_data.py and I started to train with train.py. It's been 2 or 3 hours already, and all I can see in console is "Epoch 1". How long (aprox) should an epoch take? Is it possible it takes so long? Or I do something wrong?
Hello, I find your repo very interesting and helpful. Could you please upload your inference code? Thank you
Hello, thank you for your code. I have a question about the Mall, in many places, we should make use of the feat to build roi, but I don't find any operation about the feat. So can you tell me how to deal with the roi in the dataset of Mall ?
Looking forward your reply!
I hope you will provide infer.py for inference from image.
Thank you !
h5.create_dataset('images', (size, in_channels, *img_size))
Can you elaborate this statement, specially '*img_size' whats mean?
Hello,
Can I use my own custom dataset?
Thanks
Can you provide the pretrained checkpoint if there is no copyrights issues?
Hello,Is the generated h5 file (train.h5/valid.h5)a collection of h5 images generated by each image? Thank you
I'm new in python but used to program on Matlab. I would like to reproduce this example. The network seems to work fine but I don't understand why the plots aren't work. Tried everything, but I can't see nothing either on Spyder or PyCharm. How do I get the plot working? Thanks.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.