RuntimeError: Given groups=1, weight of size [768, 3, 16, 16], expected input[1, 1, 256, 192] to have 3 channels, but got 1 channels instead

[mxyqsh]

#========= [Train Configs] =========#
# - Num GPUs: 1
# - Batch size (per gpu): 1
# - LR:  0.000063
# - Num params: 89,994,513
# - AMP: True
#===================================# 

🏋️> Epoch [000/210] | Loss 0.0014 | LR 0.000006 | Step: 0%| | 51/149813 [00:08<6:55:19, 6.01it/s]] Traceback (most recent call last): File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/train.py", line 163, in main() File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/click/core.py", line 1130, in call return self.main(*args, **kwargs) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/click/core.py", line 1055, in main rv = self.invoke(ctx) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/click/core.py", line 1404, in invoke return ctx.invoke(self.callback, **ctx.params) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/click/core.py", line 760, in invoke return __callback(*args, **kwargs) File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/train.py", line 150, in main train_model( File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/utils/train_valid_fn.py", line 131, in train_model outputs = model(images) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward return self.module(*inputs[0], **kwargs[0]) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/models/model.py", line 24, in forward return self.keypoint_head(self.backbone(x)) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/models/backbone/vit.py", line 399, in forward x = self.forward_features(x) File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/models/backbone/vit.py", line 379, in forward_features x, (Hp, Wp) = self.patch_embed(x) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/ubuntu/mxy/workspace/ViTPose_pytorch/models/backbone/vit.py", line 226, in forward x = self.proj(x) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/conv.py", line 457, in forward return self._conv_forward(input, self.weight, self.bias) File "/home/ubuntu/anaconda3/envs/vitpose/lib/python3.9/site-packages/torch/nn/modules/conv.py", line 453, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Given groups=1, weight of size [768, 3, 16, 16], expected input[1, 1, 256, 192] to have 3 channels, but got 1 channels instead