InvalidSubmission:
Traceback (most recent call last):
File "/workspace/src/duckietown-challenges/src/duckietown_challenges/cie_concrete.py", line 486, in wrap_evaluator
raise InvalidSubmission(out[SPECIAL_INVALID_SUBMISSION])
InvalidSubmission: Invalid solution:
Traceback (most recent call last):
File "/workspace/src/duckietown-challenges/src/duckietown_challenges/cie_concrete.py", line 590, in wrap_solution
raise InvalidSubmission(msg)
InvalidSubmission: Uncaught exception in solution:
Traceback (most recent call last):
File "/workspace/src/duckietown-challenges/src/duckietown_challenges/cie_concrete.py", line 585, in wrap_solution
solution.run(cis)
File "solution.py", line 117, in run
solve(params, cis)
File "solution.py", line 64, in solve
model = Model(config_name=config_name, config=config)
File "/workspace/model.py", line 15, in __init__
self.init_model(config_name)
File "/workspace/model.py", line 45, in init_model
map_location=self.device))
File "/opt/conda/lib/python2.7/site-packages/torch/nn/modules/module.py", line 719, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for NoisyDQN:
size mismatch for cnn.conv1.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv1.weight: copying a param of torch.Size([256, 3, 7, 7]) from checkpoint, where the shape is torch.Size([64, 3, 7, 7]) in current model.
size mismatch for cnn.bn1.running_var: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn1.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn1.weight: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn1.running_mean: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv2.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv2.weight: copying a param of torch.Size([256, 256, 5, 5]) from checkpoint, where the shape is torch.Size([64, 64, 5, 5]) in current model.
size mismatch for cnn.bn2.running_var: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn2.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn2.weight: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn2.running_mean: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv3.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv3.weight: copying a param of torch.Size([256, 256, 3, 3]) from checkpoint, where the shape is torch.Size([64, 64, 3, 3]) in current model.
size mismatch for cnn.bn3.running_var: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn3.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn3.weight: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn3.running_mean: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv4.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.conv4.weight: copying a param of torch.Size([256, 256, 3, 3]) from checkpoint, where the shape is torch.Size([64, 64, 3, 3]) in current model.
size mismatch for cnn.bn4.running_var: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn4.bias: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn4.weight: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for cnn.bn4.running_mean: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for noisy2.weight_epsilon: copying a param of torch.Size([5, 256]) from checkpoint, where the shape is torch.Size([5, 64]) in current model.
size mismatch for noisy2.weight_mu: copying a param of torch.Size([5, 256]) from checkpoint, where the shape is torch.Size([5, 64]) in current model.
size mismatch for noisy2.weight_sigma: copying a param of torch.Size([5, 256]) from checkpoint, where the shape is torch.Size([5, 64]) in current model.
size mismatch for noisy1.bias_sigma: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for noisy1.weight_epsilon: copying a param of torch.Size([256, 1024]) from checkpoint, where the shape is torch.Size([64, 256]) in current model.
size mismatch for noisy1.weight_mu: copying a param of torch.Size([256, 1024]) from checkpoint, where the shape is torch.Size([64, 256]) in current model.
size mismatch for noisy1.weight_sigma: copying a param of torch.Size([256, 1024]) from checkpoint, where the shape is torch.Size([64, 256]) in current model.
size mismatch for noisy1.bias_mu: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
size mismatch for noisy1.bias_epsilon: copying a param of torch.Size([256]) from checkpoint, where the shape is torch.Size([64]) in current model.
Artefacts hidden. If you are the author, please login using the top-right link or use the dashboard.