search

harvitronix / reinforcement-learning-car

Using reinforcement learning to teach a car to avoid obstacles.
MIT License
488 stars 202 forks source link

Error in playing.py #25

Closed SaiSudhamsa closed 5 years ago

SaiSudhamsa commented 5 years ago

When I run the playing.py file, I get the following error ValueError: Dimension 0 in both shapes must be equal, but are 3 and 6. Shapes are [3,164] and [6,164]. for 'Assign' (op: 'Assign') with input shapes: [3,164], [6,164].

I am using version 2.0.0

Traceback (most recent call last): File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1659, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimension 0 in both shapes must be equal, but are 3 and 6. Shapes are [3,164] and [6,164]. for 'Assign' (op: 'Assign') with input shapes: [3,164], [6,164].

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "playing.py", line 38, in model = neural_net(NUM_SENSORS, [164, 150], saved_model) File "/home/sudhamsa/reinforcement-learning-car-2.0.0/nn.py", line 46, in neural_net model.load_weights(load) File "/home/sudhamsa/.local/lib/python3.6/site-packages/keras/engine/network.py", line 1166, in load_weights f, self.layers, reshape=reshape) File "/home/sudhamsa/.local/lib/python3.6/site-packages/keras/engine/saving.py", line 1058, in load_weights_from_hdf5_group K.batch_set_value(weight_value_tuples) File "/home/sudhamsa/.local/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2465, in batch_set_value assign_op = x.assign(assign_placeholder) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/ops/variables.py", line 1762, in assign name=name) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/ops/state_ops.py", line 223, in assign validate_shape=validate_shape) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_state_ops.py", line 64, in assign use_locking=use_locking, name=name) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op op_def=op_def) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1823, in init control_input_ops) File "/home/sudhamsa/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1662, in _create_c_op raise ValueError(str(e)) ValueError: Dimension 0 in both shapes must be equal, but are 3 and 6. Shapes are [3,164] and [6,164]. for 'Assign' (op: 'Assign') with input shapes: [3,164], [6,164].