关于deeplabV3+ cropsize的说明

使用deeplabV3+做语义分割自训练模型关于cropsize需要注意的地方;

python deeplab/train.py \
--logtostderr \
--train_split="train" \
--model_variant="xception_65" \
--atrous_rates=6 \
--atrous_rates=12 \
--atrous_rates=18 \
--output_stride=16 \
--decoder_output_stride=4 \
--train_crop_size=513 \
--train_crop_size=513 \
--train_batch_size=4 \
--dataset="railway" \
--training_number_of_steps=30000 \
--fine_tune_batch_norm=false \
--tf_initial_checkpoint="deeplab/datasets/railway/init_models/deeplabv3_pascal_train_aug/model.ckpt" \
--train_logdir="deeplab/datasets/railway/train" \
--dataset_dir="deeplab/datasets/railway/tfrecord" 

其中有两项参数为

--train_crop_size=513 \
--train_crop_size=513 \

此时为输入源图像的随机裁剪，当前如果你的GPU够强大，也可以不裁剪，原图大小输入，如果你的GPU显存不够，可以减小

--train_batch_size=4

最后需要注意的是，这里的cropsize决定了eval.py中的eval_crop_size的大小，若此处为（513，513），eval.py中就不能大于513，否则会报错。

InvalidArgumentError                      Traceback (most recent call last)
~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1321     try:
-> 1322       return fn(*args)
   1323     except errors.OpError as e:

~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
   1306       return self._call_tf_sessionrun(
-> 1307           options, feed_dict, fetch_list, target_list, run_metadata)
   1308 

~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
   1408           self._session, options, feed_dict, fetch_list, target_list,
-> 1409           run_metadata)
   1410     else:

InvalidArgumentError: padded_shape[1]=87 is not divisible by block_shape[1]=2
	 [[Node: xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND = SpaceToBatchND[T=DT_FLOAT, Tblock_shape=DT_INT32, Tpaddings=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](xception_65/exit_flow/block1/unit_1/xception_module/ArithmeticOptimizer/AddOpsRewrite_add-0-0-TransposeNCHWToNHWC-LayoutOptimizer, xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND/block_shape, xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND/paddings)]]

During handling of the above exception, another exception occurred:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-30-3de39f77875f> in <module>
     28 image_path = '/home/user07/tensorflow/models/research/deeplab/datasets/railway/image/666.jpg'
     29 original_im = Image.open(image_path)
---> 30 resized_im, seg_map = MODEL.run(original_im)
     31 
     32 cv2.imwrite("test.jpg",seg_map)

<ipython-input-28-ca0f7480dd16> in run(self, image)
     50     batch_seg_map = self.sess.run(
     51         self.OUTPUT_TENSOR_NAME,
---> 52         feed_dict={self.INPUT_TENSOR_NAME: [np.asarray(resized_image)]})
     53     seg_map = batch_seg_map[0]
     54     return resized_image, seg_map

~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    898     try:
    899       result = self._run(None, fetches, feed_dict, options_ptr,
--> 900                          run_metadata_ptr)
    901       if run_metadata:
    902         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1133     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1134       results = self._do_run(handle, final_targets, final_fetches,
-> 1135                              feed_dict_tensor, options, run_metadata)
   1136     else:
   1137       results = []

~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1314     if handle is None:
   1315       return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1316                            run_metadata)
   1317     else:
   1318       return self._do_call(_prun_fn, handle, feeds, fetches)

~/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1333         except KeyError:
   1334           pass
-> 1335       raise type(e)(node_def, op, message)
   1336 
   1337   def _extend_graph(self):

InvalidArgumentError: padded_shape[1]=87 is not divisible by block_shape[1]=2
	 [[Node: xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND = SpaceToBatchND[T=DT_FLOAT, Tblock_shape=DT_INT32, Tpaddings=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](xception_65/exit_flow/block1/unit_1/xception_module/ArithmeticOptimizer/AddOpsRewrite_add-0-0-TransposeNCHWToNHWC-LayoutOptimizer, xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND/block_shape, xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND/paddings)]]

Caused by op 'xception_65/exit_flow/block2/unit_1/xception_module/separable_conv1_depthwise/depthwise/SpaceToBatchND', defined at:
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
    app.start()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 505, in start
    self.io_loop.start()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/platform/asyncio.py", line 148, in start
    self.asyncio_loop.run_forever()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/asyncio/base_events.py", line 427, in run_forever
    self._run_once()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/asyncio/base_events.py", line 1440, in _run_once
    handle._run()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/asyncio/events.py", line 145, in _run
    self._callback(*self._args)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/ioloop.py", line 690, in <lambda>
    lambda f: self._run_callback(functools.partial(callback, future))
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/ioloop.py", line 743, in _run_callback
    ret = callback()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 781, in inner
    self.run()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 742, in run
    yielded = self.gen.send(value)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 370, in dispatch_queue
    yield self.process_one()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 225, in wrapper
    runner = Runner(result, future, yielded)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 708, in __init__
    self.run()
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 742, in run
    yielded = self.gen.send(value)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 357, in process_one
    yield gen.maybe_future(dispatch(*args))
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 209, in wrapper
    yielded = next(result)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 267, in dispatch_shell
    yield gen.maybe_future(handler(stream, idents, msg))
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 209, in wrapper
    yielded = next(result)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 534, in execute_request
    user_expressions, allow_stdin,
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tornado/gen.py", line 209, in wrapper
    yielded = next(result)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 294, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 536, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2848, in run_cell
    raw_cell, store_history, silent, shell_futures)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2874, in _run_cell
    return runner(coro)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/IPython/core/async_helpers.py", line 67, in _pseudo_sync_runner
    coro.send(None)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3049, in run_cell_async
    interactivity=interactivity, compiler=compiler, result=result)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3214, in run_ast_nodes
    if (yield from self.run_code(code, result)):
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3296, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-29-d8532a2f4137>", line 27, in <module>
    MODEL = DeepLabModel(model_path)
  File "<ipython-input-28-ca0f7480dd16>", line 31, in __init__
    tf.import_graph_def(graph_def, name='')
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 432, in new_func
    return func(*args, **kwargs)
  File "/home/user07/anaconda3/envs/hss_tf/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 442, in import_graph_def
    _ProcessNewOps(gr