weiyx16 / active-perception Goto Github PK

Hello, you have done a really awaresome work. I am wondering where can I find a complete version of the paper. Is there a complete manuscript that could be provided? Many thanks.

Hi, I use the cmd:

python main.py --is_train=True

It shows that No module named 'dqn'. But I find there is dqn folder.
Maybe the error is from

from dqn.agent import Agent

Could you please help me?

Greatings!

I am trying to run your code for a university project, however i am facing the fact that it says "No module named tensorflow" even tough i have it installed as you can see in the prints below. What can I do to solve this problem?

Hello, I am recently running your code in ubuntu16.04, ros kinetic, and v-rep 3.6.1. When I start the simulation of V-rep scene, and run the command "python main.py --is_train=True" to perform training, the following error occurs. It seems that the affordance map cannot be created in the former step of "os.system(affordance_cmd)". Would you please help me with this issue? Thanks a lot! The log is as follows:

(active-perception) ys@huang:~/Active-Perception/DQN$ python main.py --is_train=True
/home/ys/anaconda3/envs/active-perception/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
return f(args, **kwds)
/home/ys/anaconda3/envs/active-perception/lib/python3.6/site-packages/h5py/init.py:34: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
--- Successfully load vrep ---
[] Use GPU Fraction is : 0.6000
2019-09-25 20:43:31.029367: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA

[*] Current Configuration
{'Lua_PATH': '../affordance_model/infer.lua',
'batch_size': 16,
'ckpt_dir': './dqn/checkpoint',
'cnn_format': 'NHWC',
'discount': 0.6,
'end_metric': 0.85,
'env_name': 'Act_Perc',
'ep_end': 0.2,
'ep_end_t': 10000.0,
'ep_start': 1.0,
'history_length': 4,
'inChannel': 4,
'is_sim': True,
'is_train': True,
'learn_start': 200.0,
'learning_rate': 0.001,
'learning_rate_decay': 0.96,
'learning_rate_decay_step': 200,
'learning_rate_minimum': 0.00025,
'max_reward': 1.0,
'max_step': 20000,
'memory_size': 2500,
'min_reward': -1.0,
'model_dir': './dqn/model',
'scale': 50,
'scene_num': 24,
'screen_height': 128,
'screen_width': 128,
'target_q_update_step': 50,
'test_scene_num': 6,
'test_step': 200,
'train_frequency': 4}
Simulation started
Connection success!

[] Initialize the simulation environment
[] Build Deep Q-Network
[] Build Q-Evaluate Scope
[] Build Q-Target Scope
[] Build Weights Transform Scope
[] Build Optimize Scope
[] Build Summary Scope
[] Initial All Variables
[] Loading checkpoints...
[] Load SUCCESS: ./dqn/checkpoint/dqn_model_ckpt-13400
[] Assign Weights from Prediction to Target
[] Random init the scene 13 with 0 object removed
/home/ys/torch/install/bin/luajit: cannot open <../affordance_model/model.t7> in mode r at /home/ys/torch/pkg/torch/lib/TH/THDiskFile.c:673
stack traceback:
[C]: at 0x7fb4af384440
[C]: in function 'DiskFile'
/home/ys/torch/install/share/lua/5.1/torch/File.lua:405: in function 'load'
../affordance_model/infer.lua:36: in main chunk
[C]: in function 'dofile'
...e/ys/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
Traceback (most recent call last):
File "main.py", line 88, in
tf.app.run()
File "/home/ys/anaconda3/envs/active-perception/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "main.py", line 72, in main
agent.train()
File "/home/ys/Active-Perception/DQN/dqn/agent_18.py", line 50, in train
screen, reward, action, terminal = self.env.new_scene()
File "/home/ys/Active-Perception/DQN/simulation/environment.py", line 483, in new_scene
self.screen, self.local_afford_past, self.location_2d = self.camera.local_patch(self.index, (self.screen_height, self.screen_width))
File "/home/ys/Active-Perception/DQN/simulation/environment.py", line 211, in local_patch
raise Exception(' [!] !!!!!!!!!!! Error occurred during creating affordance map')
Exception: [!] !!!!!!!!!!! Error occurred during creating affordance map

The checkpoint file in DQN/dqn/checkpoint seems to be invalid.
self.load_model() in agent_8.py returns the following error

[*] Loading checkpoints...
2019-07-23 16:57:57.724805: W tensorflow/core/framework/op_kernel.cc:1275] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key prediction/7_lq_1/biases not found in checkpoint
Traceback (most recent call last):
  File "/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1278, in _do_call
    return fn(*args)
  File "/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1263, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1350, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.NotFoundError: Key prediction/7_lq_1/biases not found in checkpoint
	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

During handling of the above exception, another exception occurred:

etc...

dqn_model_ckpt-13400.data-00000-of-00001 seems to contain the model data. However, my attempt to load this as checkpoint is unsuccessful too.

 [*] Loading checkpoints...
 [!] Load FAILED: ./dqn/checkpoint
 [*] Created model with fresh parameters.

Hi, I'm testing your environment now.
It ends quickly with 'Simulation ended!' when I type python main.py --is_train=True.
Could you please tell me how to train my own model?
I'm sorry to bother you again.

Hello, Wei, when I am training the agent in the V-rep simulator, there will always occur a ValueError of "inconsistent shape (x, 128, 3) with (128, 128, 3)". Do you have any idea with this issue? Part of the log is as follows:

-- Maximum Location at [210 227]
-- Metric for current frame: 0.734154
With peak_dis: 0.173634, flatten: 0.820850, max_value: 0.924716
13478it [15:28, 9.80s/it]
-- Push from [152. 198.] to [106.74516600406096, 243.25483399593904]

-- Maximum Location at [180 340]
-- Metric for current frame: 0.769855
With peak_dis: 0.264738, flatten: 0.859865, max_value: 0.852448
13479it [15:38, 9.88s/it]
-- Push from [193. 311.] to [257.0, 311.0]

-- Maximum Location at [175 349]
-- Metric for current frame: 0.880095
With peak_dis: 1.000000, flatten: 0.890577, max_value: 0.785750
[!!] Nearest distance: 0.084278
[*] Update the scene 16 with 3 object removed

-- Maximum Location at [175 349]
-- Metric for current frame: 0.880095
With peak_dis: 1.000000, flatten: 0.890577, max_value: 0.785750
13480it [15:57, 12.57s/it]
-- Push from [146. 398.] to [210.0, 398.0]

-- Maximum Location at [370 335]
Traceback (most recent call last):
File "main.py", line 88, in
tf.app.run()
File "/home/ys/anaconda3/envs/active-perception/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "main.py", line 72, in main
agent.train()
File "/home/ys/Active-Perception/DQN/dqn/agent_18.py", line 66, in train
screen, reward, terminal = self.env.act(action, if_train=True)
File "/home/ys/Active-Perception/DQN/simulation/environment.py", line 517, in act
self.screen, self.local_afford_new, self.location_2d = self.camera.local_patch(self.index, (self.screen_height, self.screen_width))
File "/home/ys/Active-Perception/DQN/simulation/environment.py", line 222, in local_patch
return get_patch(location_2d, self.cur_color, self.cur_depth, post_afford, patch_size)
File "/home/ys/Active-Perception/DQN/util/utils.py", line 44, in get_patch
patch_rgbd[:,:,0:3] = patch_color
ValueError: could not broadcast input array from shape (118,128,3) into shape (128,128,3)

Hi Dear

I tried to run the code but I got this sort of error
ImportError: libpcl_visualization.so.1.8: cannot open shared object file: No such file or directory

I have tried to install the pcl module but I face the same problem!!!
may I got a help to settle this issue

I would appreciate your help