I've installed Tensorflow on a Macbook Pro M1 Max Pro by first using Anaconda to install the dependencies:
conda install -c apple tensorflow-deps
Then after, I install the Tensorflow distribution that is specific for the M1 architecture and additionally a toolkit that works with the Metal GPUs:
pip install tensorflow-metal tensorflow-macos
I then write a very simple feedforward architecture with some dummy training and validation data to see if I can execute a training session:
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
from tensorflow.keras import layers
import numpy as np
model = Sequential([layers.Input((3, 1)),
layers.LSTM(64),
layers.Dense(32, activation='relu'),
layers.Dense(32, activation='relu'),
layers.Dense(1)])
model.compile(loss='mse',
optimizer=Adam(learning_rate=0.001),
metrics=['mean_absolute_error'])
X_train = np.random.rand(100,3)
y_train = np.random.rand(100)
X_val = np.random.rand(100,3)
y_val = np.random.rand(100)
model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=100)
When I execute this, I get the following errors:
File ~/test.py:20
18 X_val = np.random.rand(100,3)
19 y_val = np.random.rand(100)
---> 20 model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=100)
File ~/anaconda3/envs/cv/lib/python3.8/site-packages/keras/utils/traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.__traceback__)
68 # To get the full stack trace, call:
69 # `tf.debugging.disable_traceback_filtering()`
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
File ~/anaconda3/envs/cv/lib/python3.8/site-packages/tensorflow/python/eager/execute.py:52, in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
50 try:
51 ctx.ensure_initialized()
---> 52 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
53 inputs, attrs, num_outputs)
54 except core._NotOkStatusException as e:
55 if name is not None:
NotFoundError: Graph execution error:
Detected at node 'StatefulPartitionedCall_7' defined at (most recent call last):
File "/Users/rphan/anaconda3/envs/cv/bin/ipython", line 8, in <module>
sys.exit(start_ipython())
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/__init__.py", line 123, in start_ipython
return launch_new_instance(argv=argv, **kwargs)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/traitlets/config/application.py", line 1041, in launch_instance
app.start()
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/terminal/ipapp.py", line 318, in start
self.shell.mainloop()
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/terminal/interactiveshell.py", line 685, in mainloop
self.interact()
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/terminal/interactiveshell.py", line 678, in interact
self.run_cell(code, store_history=True)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 2940, in run_cell
result = self._run_cell(
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 2995, in _run_cell
return runner(coro)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/async_helpers.py", line 129, in _pseudo_sync_runner
coro.send(None)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 3194, in run_cell_async
has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 3373, in run_ast_nodes
if await self.run_code(code, result, async_=asy):
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 3433, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-2-0ed839f9b556>", line 1, in <module>
get_ipython().run_line_magic('run', 'test.py')
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 2364, in run_line_magic
result = fn(*args, **kwargs)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/magics/execution.py", line 829, in run
run()
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/magics/execution.py", line 814, in run
runner(filename, prog_ns, prog_ns,
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 2797, in safe_execfile
py3compat.execfile(
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/IPython/utils/py3compat.py", line 55, in execfile
exec(compiler(f.read(), fname, "exec"), glob, loc)
File "/Users/rphan/test.py", line 20, in <module>
model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=100)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 65, in error_handler
return fn(*args, **kwargs)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/engine/training.py", line 1650, in fit
tmp_logs = self.train_function(iterator)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/engine/training.py", line 1249, in train_function
return step_function(self, iterator)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/engine/training.py", line 1233, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/engine/training.py", line 1222, in run_step
outputs = model.train_step(data)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/engine/training.py", line 1027, in train_step
self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/optimizers/optimizer_experimental/optimizer.py", line 527, in minimize
self.apply_gradients(grads_and_vars)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/optimizers/optimizer_experimental/optimizer.py", line 1140, in apply_gradients
return super().apply_gradients(grads_and_vars, name=name)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/optimizers/optimizer_experimental/optimizer.py", line 634, in apply_gradients
iteration = self._internal_apply_gradients(grads_and_vars)
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/optimizers/optimizer_experimental/optimizer.py", line 1166, in _internal_apply_gradients
return tf.__internal__.distribute.interim.maybe_merge_call(
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/optimizers/optimizer_experimental/optimizer.py", line 1216, in _distributed_apply_gradients_fn
distribution.extended.update(
File "/Users/rphan/anaconda3/envs/cv/lib/python3.8/site-packages/keras/optimizers/optimizer_experimental/optimizer.py", line 1211, in apply_grad_to_update_var
return self._update_step_xla(grad, var, id(self._var_key(var)))
Node: 'StatefulPartitionedCall_7'
could not find registered platform with id: 0x1056be9e0
[[{{node StatefulPartitionedCall_7}}]] [Op:__inference_train_function_4146]
I have no idea what these errors mean. Has someone seen these errors before? This seems to be a very simple network and I can't seem to understand why the training doesn't execute.
CodePudding user response：
After extensive searching, this is due to the dependencies with Anaconda compared to the Tensorflow version installed via pip:
conda list | grep tensorflow
tensorflow-deps 2.9.0 0 apple
tensorflow-estimator 2.11.0 pypi_0 pypi
tensorflow-macos 2.11.0 pypi_0 pypi
tensorflow-metal 0.7.0 pypi_0 pypi
The version of Tensorflow I have installed does not match the Tensorflow dependencies, hence the error. The solution was to downgrade to the same version as the dependencies as well as downgrade tensorflow-metal:
pip install tensorflow-metal==0.5.0
pip install tensorflow-macos==2.9.0
Once I did this and ran the sample code, the training was successful.