mbolleng2303
commented
2 years ago Hi ! This is not the finished version of the code. You can contact me by email (maxime.bollengier@ulb.be) if you need some informations.
Open 302850047 opened 2 years ago
mbolleng2303
commented
2 years ago Hi ! This is not the finished version of the code. You can contact me by email (maxime.bollengier@ulb.be) if you need some informations.
Using backend: pytorch cuda available with GPU: GeForce RTX 3090 [I] Loading dataset Task082_BraTS2020... train, val sizes : 296 73 [I] Finished loading. [I] Data load time: 0.1132s MODEL DETAILS:
MODEL/Total parameters: GNet 15666 Training Graphs: 296 Validation Graphs: 73 Number of Classes: 1 Epoch 0: 0%| | 0/1000 [00:00<?, ?it/s] Traceback (most recent call last): File "/data/chenzhi/Chenjy/Master_Thesis-main/Train/train.py", line 29, in train_epoch_sparse batch_pos_enc = batch_graphs.ndata['pos_enc'].to(device) File "/data/chenzhi/.conda/envs/Chenjy/lib/python3.7/site-packages/dgl/view.py", line 66, in getitem return self._graph._get_n_repr(self._ntid, self._nodes)[key] File "/data/chenzhi/.conda/envs/Chenjy/lib/python3.7/site-packages/dgl/frame.py", line 393, in getitem return self._columns[name].data KeyError: 'pos_enc'
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "/data/chenzhi/Chenjy/Master_Thesis-main/main_u_net.py", line 404, in
main()
File "/data/chenzhi/Chenjy/Master_Thesis-main/main_u_net.py", line 401, in main
train_val_pipeline(MODEL_NAME, dataset, params, net_params, dirs)
File "/data/chenzhi/Chenjy/Master_Thesis-main/main_u_net.py", line 162, in train_val_pipeline
epoch)
File "/data/chenzhi/Chenjy/Master_Thesis-main/Train/train.py", line 37, in train_epoch_sparse
batch_scores = model.forward(batch_graphs, batch_x, batch_e)
File "/data/chenzhi/Chenjy/Master_Thesis-main/Network/G_u_net.py", line 37, in forward
hs = self.embed(a, hs)
File "/data/chenzhi/Chenjy/Master_Thesis-main/Network/G_u_net.py", line 44, in embed
h = self.embed_one(gs, hs)
File "/data/chenzhi/Chenjy/Master_Thesis-main/Network/G_u_net.py", line 52, in embed_one
h = self.s_gcn(g, h)
File "/data/chenzhi/.conda/envs/Chenjy/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/data/chenzhi/Chenjy/Master_Thesis-main/Layers/unet_graph_layer.py", line 59, in forward
h = torch.matmul(g, h.float())
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument vec in method wrapper__mv)
Process finished with exit code 1
The dataset is Brats2020