tensorflow docker looks like it’s broken.
My Dockerfile:
FROM nvcr.io/nvidia/l4t-tensorflow:r32.7.1-tf2.7-py3
RUN python3 -m pip install tensorflow_datasets
Running with
docker build -t trt_example --file Dockerfile .
docker run -it --rm --gpus all --privileged --name "" --volume $PWD:/src:rw trt_example bash
I am running this python3 file:
import tensorflow as tf
import tensorflow_datasets as tfds
(ds_train, ds_test), ds_info = tfds.load(
'mnist',
split=['train', 'test'],
shuffle_files=True,
as_supervised=True,
with_info=True,
)
def normalize_img(image, label):
"""Normalizes images: `uint8` -> `float32`."""
return tf.cast(image, tf.float32) / 255., label
ds_train = ds_train.map(
normalize_img, num_parallel_calls=tf.data.AUTOTUNE)
ds_train = ds_train.cache()
ds_train = ds_train.shuffle(ds_info.splits['train'].num_examples)
ds_train = ds_train.batch(128)
ds_train = ds_train.prefetch(tf.data.AUTOTUNE)
ds_test = ds_test.map(
normalize_img, num_parallel_calls=tf.data.AUTOTUNE)
ds_test = ds_test.batch(128)
ds_test = ds_test.cache()
ds_test = ds_test.prefetch(tf.data.AUTOTUNE)
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(10)
])
model.compile(
optimizer=tf.keras.optimizers.Adam(0.001),
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=[tf.keras.metrics.SparseCategoricalAccuracy()],
)
model.fit(
ds_train,
epochs=6,
validation_data=ds_test,
)
model.save("saved_model")
But it crashes with:
e.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 4321 MB memory: -> device: 0, name: Xavier, pci bus id: 0000:00:00.0, compute capability: 7.2
Epoch 1/6
Traceback (most recent call last):
File "main.py", line 43, in <module>
validation_data=ds_test,
File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1384, in fit
tmp_logs = self.train_function(iterator)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py", line 910, in __call__
result = self._call(*args, **kwds)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py", line 958, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py", line 781, in _initialize
*args, **kwds))
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py", line 3157, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py", line 3557, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py", line 3402, in _create_graph_function
capture_by_value=self._capture_by_value),
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py", line 1143, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py", line 672, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py", line 1129, in autograph_handler
raise e.ag_error_metadata.to_exception(e)
AttributeError: in user code:
File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1021, in train_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1010, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 1000, in run_step **
outputs = model.train_step(data)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/training.py", line 863, in train_step
self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
File "/usr/local/lib/python3.6/dist-packages/keras/optimizer_v2/optimizer_v2.py", line 532, in minimize
return self.apply_gradients(grads_and_vars, name=name)
File "/usr/local/lib/python3.6/dist-packages/keras/optimizer_v2/optimizer_v2.py", line 668, in apply_gradients
grads_and_vars = self._aggregate_gradients(grads_and_vars)
File "/usr/local/lib/python3.6/dist-packages/keras/optimizer_v2/optimizer_v2.py", line 484, in _aggregate_gradients
return self.gradient_aggregator(grads_and_vars)
File "/usr/local/lib/python3.6/dist-packages/keras/optimizer_v2/utils.py", line 33, in all_reduce_sum_gradients
if tf.__internal__.distribute.strategy_supports_no_merge_call():
AttributeError: module 'tensorflow.compat.v2.__internal__.distribute' has no attribute 'strategy_supports_no_merge_call'
Tried downgrading keras to 2.7.0, with this Dockerfile:
FROM nvcr.io/nvidia/l4t-tensorflow:r32.7.1-tf2.7-py3
RUN python3 -m pip install tensorflow_datasets keras==2.7.0
The first python script runs, but it breaks in conversion:
from tensorflow.python.compiler.tensorrt import trt_convert as trt
import tensorflow as tf
converter = trt.TrtGraphConverterV2(input_saved_model_dir="saved_model")
converter.convert()
converter.save("output")