Hello ,
I am working on implementing the keras model in TVM. I have tried to run a
tutorial model of keras, which was from the tvm tutorials for compiling
deep learning models. When I tried to compile a few weeks ago , it was
working fine. But now it's not working.
The following is the error log:
python3 from_keras.py
2021-10-14 15:25:53.543359: W
tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not
load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0:
cannot open shared object file: No such file or directory
2021-10-14 15:25:53.543392: I
tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart
dlerror if you do not have a GPU set up on your machine.
2021-10-14 15:25:54.956410: W
tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not
load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open
shared object file: No such file or directory
2021-10-14 15:25:54.956442: W
tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit:
UNKNOWN ERROR (303)
2021-10-14 15:25:54.956472: I
tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does
not appear to be running on this host (udeshkohli18-MacBookAir):
/proc/driver/nvidia/version does not exist
2021-10-14 15:25:54.956676: I
tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary
is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the
following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate
compiler flags.
(1, 224, 224, 3)
input_1 (1, 3, 224, 224)
Traceback (most recent call last):
File "from_keras.py", line 104, in <module>
mod, params = relay.frontend.from_keras(keras_resnet50, shape_dict)
File "/home/udeshkohli18/tvm/python/tvm/relay/frontend/keras.py", line
1233, in from_keras
input_layer_class = keras.engine.InputLayer
AttributeError: module 'keras.engine' has no attribute 'InputLayer'
I have tried to solve the error but failed.
Kindly help me to resolve the error.
thanks and regards,
Udesh Cuddalore
