edwardyehuang / car Goto Github PK
View Code? Open in Web Editor NEWCAR: Class-aware Regularizations for Semantic Segmentation (ECCV-2022)
License: MIT License
CAR: Class-aware Regularizations for Semantic Segmentation (ECCV-2022)
License: MIT License
I am trying the code while stopped at step 2. I can not convert downloaded dataset. the final error is related to os.fspath. I am wondering there might be something wrong about the output path part. What should inside the { }? Can you give an example for it?
HI. Is it possible to upload a converted dataset?
I tried the new code as:
sudo python3 ids/tools/convert_record.py --convert_datasets=pascalcontext --pascalcontext_path=/home/xuanwu/Downloads/CAR/pascalcontext --tfrecord_outputs=/home/xuanwu/Downloads/CAR/conv
where conv is the output position.
However, the conversion stopped at 'conversion 2794'. The terminal stopped and exited with no no message. Can you help?
Hello, I'm very interested in your work, but when I run train Py, I received the following error.
In addition, I used the CONDA environment and installed TF2.8 and cudnn8.1
2022-05-05 10:33:01.148738: W tensorflow/core/framework/op_kernel.cc:1745] OP_REQUIRES failed at conv_ops.cc:1120 : UNIMPLEMENTED: DNN library is not found. Traceback (most recent call last): File "train.py", line 66, in <module> app.run(train) File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/absl/app.py", line 312, in run _run_main(main, args) File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/absl/app.py", line 258, in _run_main sys.exit(main(argv)) File "train.py", line 45, in train training.train( File "/tmpnfs/junli/CAR/iseg/core_train.py", line 142, in train model.fit( File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler raise e.with_traceback(filtered_tb) from None File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/tensorflow/python/eager/execute.py", line 54, in quick_execute tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name, tensorflow.python.framework.errors_impl.UnimplementedError: Graph execution error:
……
File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/keras/engine/base_layer.py", line 1096, in __call__ outputs = call_fn(inputs, *args, **kwargs) File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 92, in error_handler return fn(*args, **kwargs) File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/keras/layers/convolutional.py", line 248, in call outputs = self.convolution_op(inputs, self.kernel) File "/home/CN/zizhang.wu/anaconda3/envs/jlcar/lib/python3.8/site-packages/keras/layers/convolutional.py", line 233, in convolution_op return tf.nn.convolution( Node: 'seg_managed/resnet50/conv1_1_conv/Conv2D' 2 root error(s) found. (0) UNIMPLEMENTED: DNN library is not found. [[{{node seg_managed/resnet50/conv1_1_conv/Conv2D}}]] [[div_no_nan_4/ReadVariableOp/_418]] (1) UNIMPLEMENTED: DNN library is not found. [[{{node seg_managed/resnet50/conv1_1_conv/Conv2D}}]] 0 successful operations. 0 derived errors ignored. [Op:__inference_train_function_40875]
Why do you use the softmax and stop the gradient on keys?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.