gy20073 / bdd_driving_model Goto Github PK

I wonder if you ever tried to use FCN-VGG16 as the fcn part of FCN-LSTM, if I use FCN-VGG16 instead of FCN-AlexNet，do you think the performance of the model will be promoted?
Thanks.

I've been looking for vehicle detection models trained in mobilenet-ssd. heard BDD provides best vehicle detection dataset, so have anyone got it?

The part of visualization is not completed( I saw 'TODO Improved visualization' in step 'Run a pretrained Model'), right? I try to run wrapper_test.ipynb by Jupyter notebook, the first, the second cell and the first three lines of the third cell are okay, and I can see an image. How can I see some cool results just like photos in your paper?
Sorry to bother and thanks.

I am using the Google Chrome, and I find its speed is about 30kb/s. How can I download these big files in Google Drive most quickly?

Two things i want to ask:

Firstly

• The mapping of the returned logits by discrete_tcnn1 with it's classes. because the returned values are 6 and the discrete actions that you have specified in wrapper.py are 7. So what is the actual mapping

Secondly

• I am unable to load the models discrete_fcn_lstm & continuous_datadriven. Though it loads discrete_tcnn1 but fails to load other two models

Stack Trace is given below.
` File "/home/rameez/Desktop/FYP/Code/BDD_Code/BDD_Driving_Model-master/wrapper.py", line 62, in init
saver.restore(self.sess, model_path)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1560, in restore
{self.saver_def.filename_tensor_name: save_path})
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "TrainStage1_discrete_fcn_lstm/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/bias/ExponentialMovingAverage" not found in checkpoint files ./data/pre_trained/discrete_fcn_lstm/model.ckpt-315001.bestmodel
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

Caused by op u'save/RestoreV2', defined at:
File "runner.py", line 11, in
20)
File "/home/rameez/Desktop/FYP/Code/BDD_Code/BDD_Driving_Model-master/wrapper.py", line 56, in init
saver = tf.train.Saver(variables_to_restore)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1140, in init
self.build()
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1172, in build
filename=self._filename)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 688, in build
restore_sequentially, reshape)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 407, in _AddRestoreOps
tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 247, in restore_op
[spec.tensor.dtype])[0])
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 663, in restore_v2
dtypes=dtypes, name=name)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/rameez/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

NotFoundError (see above for traceback): Tensor name "TrainStage1_discrete_fcn_lstm/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/bias/ExponentialMovingAverage" not found in checkpoint files ./data/pre_trained/discrete_fcn_lstm/model.ckpt-315001.bestmodel
[[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]`

可否放百度网盘呢？

there says "Download and unzip the dataset's training and validation set into some directory $DATA_ROOT. There should be directories like $DATA_ROOT/train/videos and $DATA_ROOT/val/info."in the README.md
But where to get the dataset? In berkley DeepDrive, i cannot download the info.
Thank u so much if anyboby could help me.

Hi, I'm trying to create a baseline with a discrete model on a small part of BDDV (1000 samples), but it only outputs straight class in case of no weighted training, and stop during weighted. Has anybody succeeded in reproducing the results? What can be the error, is it more to data part or I'm missing something?

Has anyone tried the model of continuous_datadriven_bin? I use the file model.ckpt-261001.bestmodel and the output is np.array([1, 362]). However, its argmax is always 87

On passing any type of image as an input there is no change in the yaw_rate from 0.
It always selects the 87th bin and whose value lies the the range of [-small_angle +small_angle] so the resulting value becomes zero.
I am passing three images consecutively as an input which are appended in latest_frames in the function observe_a_frame in wrapper.py.
Is there any further changes required to get these values correctly.
(This issue is only with the yaw_rate velocity is changing)

Thanks

I have a problem trying to run "wrapper_test.ipynb".
There is no * .tfrecords file.

I'm going to try to create a "*.tfrecords" file by looking at the data preparation description in README.md.
but I can not find the link or url to download the datasets.

How can I get the original video dataset?

Hi, @gy20073 ,

When will the BDD-V dataset be released?

I get the following message when I run "python config.py train discrete_tcnn1". I can't find anything about conv1/weights/Momentum, so I'm not sure what to do. Can you help with this? Thanks!

Traceback (most recent call last):
File "train.py", line 583, in
tf.app.run()
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 580, in main
train()
File "train.py", line 399, in train
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/optimizer.py", line 446, in apply_gradients
self._create_slots([_get_variable_for(v) for v in var_list])
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/momentum.py", line 66, in _create_slots
self._zeros_slot(v, "momentum", self._name)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/optimizer.py", line 766, in _zeros_slot
named_slots[_var_key(var)] = slot_creator.create_zeros_slot(var, op_name)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/slot_creator.py", line 174, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/slot_creator.py", line 146, in create_slot_with_initializer
dtype)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/slot_creator.py", line 66, in _create_slot_var
validate_shape=validate_shape)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1065, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 962, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 367, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 352, in _true_getter
use_resource=use_resource)
File "/home/zrachlin/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 682, in _get_single_variable
"VarScope?" % name)
ValueError: Variable conv1/weights/Momentum/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

hi,
Could you please tell me what's the meaning of this output of "observe a frame()"
[[ 2.78248072 1.81109738 3.15505242 0.75022471 -3.66833758 -4.27568913]]
Thanks

Hello,
Could you please explain the procedure of generating ground truth actions (stop, go ,...) from the dataset. What kind of information do you use to generate it? Do you use yaw rate, speed or do you rely on course (heading) to generate it?

Thanks.

Hi,
why eval.py is not using gpu acceleration, the verification and testing process is too slow.

Dear authors, I am a newbie on python. I have a difficulty on visualizing the the result from the single image with 'generate_visualization(img, logits, method="vis_continuous")'. What's is logit parameter? Also, how we called this parameter?

THanks

Hi,
What is the segmentation model here？And what is the label for the segmentation loss?
looking forward to your reply！

I have used the datadriven pretrained model to test it using wrapper_test on an image and the function "observe_a_frame" gives an output of 362 values and I am unable to understand what these values are and what they represent.

Hi,I have signed up.But it seem that there isn't any email to me?So how can I get the dataset?Thanks a lot~