Am getting the runtime error when the cuda device is set to Tesla K40C.
CUDA version: 11.0 NVIDIA-Driver version: 450.51.06
Kindly guide me so as to run the scripts given in examples to generate the molecules.
enc = gentrl.RNNEncoder(latent_size=50)
dec = gentrl.DilConvDecoder(latent_input_size=50)
model = gentrl.GENTRL(enc, dec, 50 * [('c', 20)], [('c', 20)], beta=0.001)
model.cuda();
RuntimeError Traceback (most recent call last)
in
2 dec = gentrl.DilConvDecoder(latent_input_size=50)
3 model = gentrl.GENTRL(enc, dec, 50 * [('c', 20)], [('c', 20)], beta=0.001)
----> 4 model.cuda();
~/anaconda3/envs/myenv/lib/python3.7/site-packages/torch/nn/modules/module.py in cuda(self, device)
461 Module: self
462 """
--> 463 return self._apply(lambda t: t.cuda(device))
464
465 def cpu(self: T) -> T:
~/anaconda3/envs/myenv/lib/python3.7/site-packages/torch/nn/modules/module.py in _apply(self, fn)
357 def _apply(self, fn):
358 for module in self.children():
--> 359 module._apply(fn)
360
361 def compute_should_use_set_data(tensor, tensor_applied):
~/anaconda3/envs/myenv/lib/python3.7/site-packages/torch/nn/modules/module.py in _apply(self, fn)
357 def _apply(self, fn):
358 for module in self.children():
--> 359 module._apply(fn)
360
361 def compute_should_use_set_data(tensor, tensor_applied):
~/anaconda3/envs/myenv/lib/python3.7/site-packages/torch/nn/modules/rnn.py in _apply(self, fn)
160 self._flat_weights = [(lambda wn: getattr(self, wn) if hasattr(self, wn) else None)(wn) for wn in self._flat_weights_names]
161 # Flattens params (on CUDA)
--> 162 self.flatten_parameters()
163
164 return ret
~/anaconda3/envs/myenv/lib/python3.7/site-packages/torch/nn/modules/rnn.py in flatten_parameters(self)
150 self._flat_weights, (4 if self.bias else 2),
151 self.input_size, rnn.get_cudnn_mode(self.mode), self.hidden_size, self.num_layers,
--> 152 self.batch_first, bool(self.bidirectional))
153
154 def _apply(self, fn):
RuntimeError: CUDA error: no kernel image is available for execution on the device
Am getting the runtime error when the cuda device is set to Tesla K40C. CUDA version: 11.0 NVIDIA-Driver version: 450.51.06 Kindly guide me so as to run the scripts given in examples to generate the molecules.
enc = gentrl.RNNEncoder(latent_size=50) dec = gentrl.DilConvDecoder(latent_input_size=50) model = gentrl.GENTRL(enc, dec, 50 * [('c', 20)], [('c', 20)], beta=0.001) model.cuda();
RuntimeError Traceback (most recent call last)