Open livecle opened 4 years ago
Got the same problem, but KeyError: 'Squeeze' (
Hello @livecle and @poormag.
I added support of Squeeze
and Floor
layers support for NCHW data format. Please, upgrade onnx2keras
library to 0.0.11
using:
pip install --upgrade onnx2keras
@nerox8664 thanx, for Squeeze its okay now
@nerox8664 thank you for your reply. It looks work now, but I got another error.
DEBUG:onnx2keras:######
DEBUG:onnx2keras:...
DEBUG:onnx2keras:Converting ONNX operation
DEBUG:onnx2keras:type: Floor
DEBUG:onnx2keras:node_name: 1196
DEBUG:onnx2keras:node_params: {'change_ordering': False, 'name_policy': 'keep'}
DEBUG:onnx2keras:...
DEBUG:onnx2keras:Check if all inputs are available:
DEBUG:onnx2keras:Check input 0 (name 1195).
DEBUG:onnx2keras:... found all, continue
Traceback (most recent call last):
File "D:\Program Files\JetBrains\PyCharm 2019.1.2\helpers\pydev\pydevd.py", line 1758, in <module>
main()
File "D:\Program Files\JetBrains\PyCharm 2019.1.2\helpers\pydev\pydevd.py", line 1752, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "D:\Program Files\JetBrains\PyCharm 2019.1.2\helpers\pydev\pydevd.py", line 1147, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "D:\Program Files\JetBrains\PyCharm 2019.1.2\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "D:/chenle/github/CenterNet.git/trunk/src/demo_test.py", line 41, in <module>
demo(opt)
File "D:/chenle/github/CenterNet.git/trunk/src/demo_test.py", line 37, in demo
k_model = pytorch_to_keras(detector.model, input_var, [(3, 512, 512,)], verbose=True,name_policy="keep",change_ordering=False)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\pytorch2keras\converter.py", line 73, in pytorch_to_keras
verbose=verbose, change_ordering=change_ordering)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\onnx2keras\converter.py", line 170, in onnx_to_keras
keras_names
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\onnx2keras\operation_layers.py", line 293, in convert_floor
layers[node_name] = lambda_layer(input_0)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\keras\engine\base_layer.py", line 489, in __call__
output = self.call(inputs, **kwargs)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\keras\layers\core.py", line 716, in call
return self.function(inputs, **arguments)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\onnx2keras\operation_layers.py", line 290, in target_layer
return tf.floor(x)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 3680, in floor
"Floor", x=x, name=name)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 610, in _apply_op_helper
param_name=input_name)
File "C:\Users\chenle\AppData\Local\conda\conda\envs\pytorch-gpu\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 60, in _SatisfiesTypeConstraint
", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: Value passed to parameter 'x' has DataType int32 not in list of allowed values: bfloat16, float16, float32, float64
Describe the bug thanks for your code I tried to convert official PyTorch centernet, the backbone is hourglass, got this error.
Logs
Environment (please complete the following information):