nephashi / deepcompression Goto Github PK

Hi nephashi,

Thanks for sharing this repo but I encountered some bugs when running the demo:
cd mnist_iterative_pruning; python iterative_prune.py -1 -2 -3.
To be more specific, it stops between step 2 (prune) and step 3 (sparse), around #L230: saver.restore(sess, "./models/model_ckpt_dense_retrained-16").

This happens in both tensorflow 1.6.0 and 1.8.0 with Python 3.6.3 on CPU. Here is the traceback.

2018-06-30 11:28:01.111980: W tensorflow/core/framework/op_kernel.cc:1202] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key b_conv1/Adam not found in checkpoint
Traceback (most recent call last):
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1361, in _do_call
return fn(*args)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1340, in _run_fn
target_list, status, run_metadata)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 516, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Key b_conv1/Adam not found in checkpoint
[[Node: save_3/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:loca
lhost/replica:0/task:0/device:CPU:0"](_arg_save_3/Const_0_0, save_3/RestoreV2/tensor_names, save_3/RestoreV2/shape_and_slices)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "iterative_prune.py", line 251, in
saver.restore(sess, "./models/model_ckpt_dense_retrained-%.2f" % float(args.percentage))
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1755, in restore
{self.saver_def.filename_tensor_name: save_path})
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 905, in run
run_metadata_ptr)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1137, in _run
feed_dict_tensor, options, run_metadata)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1355, in _do_run
options, run_metadata)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1374, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Key b_conv1/Adam not found in checkpoint
[[Node: save_3/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_3/Const_0_0, save_3/RestoreV2/tensor_names, save_3/RestoreV2/shape_and_slices)]]

Caused by op 'save_3/RestoreV2', defined at:
File "iterative_prune.py", line 248, in
saver = tf.train.Saver()
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1293, in init
self.build()
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1302, in build
self._build(self._filename, build_save=True, build_restore=True)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1339, in _build
build_save=build_save, build_restore=build_restore)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 796, in _build_internal
restore_sequentially, reshape)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 449, in _AddRestoreOps
restore_sequentially)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 847, in bulk_restore
return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1030, in restore_v2
shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3271, in create_op
op_def=op_def)
File "DeepCompression/env/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1650, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

NotFoundError (see above for traceback): Key b_conv1/Adam not found in checkpoint
[[Node: save_3/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save_3/Const_0_0, save_3/RestoreV2/tensor_names, save_3/RestoreV2/shape_and_slices)]]

System information

• Have I written custom code: No.
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): macOS 10.13.5
• TensorFlow installed from (source or binary): pip
• TensorFlow version (use command below): 1.6.0, 1.8.0
• Python version: 3.6.3
• Bazel version (if compiling from source): n/a
• GCC/Compiler version (if compiling from source): n/a
• CUDA/cuDNN version: n/a
• GPU model and memory: n/a
• Exact command to reproduce: cd mnist_iterative_pruning; python iterative_prune.py -1 -2 -3

Thanks,
Luke