search

chou141253 / FGVC-PIM

Pytorch implementation for "A Novel Plug-in Module for Fine-Grained Visual Classification". fine-grained visual classification task.
MIT License
181 stars 37 forks source link

RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x1456 and 2720x85) #24

Open smallzhu opened 2 years ago

smallzhu commented 2 years ago

When I select efficentnet for training I get the following error, only swin-transformer does not report it Can you help me?

Start Training 1 EpochTraceback (most recent call last): File "D:/hxy/FGVC-PIM-master/main.py", line 301, in main(args, tlogger) File "D:/hxy/FGVC-PIM-master/main.py", line 253, in main train(args, epoch, model, scaler, amp_context, optimizer, schedule, train_loader) File "D:/hxy/FGVC-PIM-master/main.py", line 140, in train outs = model(datas) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(*input, kwargs) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\parallel\data_parallel.py", line 168, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\parallel\data_parallel.py", line 178, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\parallel\parallel_apply.py", line 86, in parallel_apply output.reraise() File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch_utils.py", line 457, in reraise raise exception RuntimeError: Caught RuntimeError in replica 0 on device 0. Original Traceback (most recent call last): File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\parallel\parallel_apply.py", line 61, in _worker output = module(*input, *kwargs) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(input, kwargs) File "D:\hxy\FGVC-PIM-master\models\pim_module\pim_module.py", line 414, in forward comb_outs = self.combiner(selects) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(*input, *kwargs) File "D:\hxy\FGVC-PIM-master\models\pim_module\pim_module.py", line 81, in forward hs = self.param_pool0(hs) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl return forward_call(input, kwargs) File "C:\Users\mj\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\linear.py", line 103, in forward return F.linear(input, self.weight, self.bias) RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x1456 and 2720x85)**

chou141253 commented 2 years ago

How is your config file set?

smallzhu commented 2 years ago

How is your config file set?

project_name: tea_swin_t exp_name: T3000 use_wandb: True wandb_entity: dechenzhu train_root: D:\hxy\FGVC-PIM-master\dataset\data3 val_root: D:\hxy\FGVC-PIM-master\dataset\test1 data_size: 448 num_workers: 2 batch_size: 8 model_name: efficient pretrained: ~ optimizer: SGD max_lr: 0.0005 wdecay: 0.0005 max_epochs: 300 warmup_batchs: 800 use_amp: True use_fpn: True fpn_size: 1536 use_selection: True num_classes: 25 num_selects: layer1: 2048 layer2: 512 layer3: 128 layer4: 32 use_combiner: False lambda_b: 0.5 lambda_s: 0.0 lambda_n: 5.0 lambda_c: 1.0 update_freq: 2 log_freq: 100 eval_freq: 2

Chaoran-F commented 1 year ago

same question in here, backbone is EfficientNet

Chaoran-F commented 1 year ago

How is your config file set?

project_name: tea_swin_t exp_name: T3000 use_wandb: True wandb_entity: dechenzhu train_root: D:\hxy\FGVC-PIM-master\dataset\data3 val_root: D:\hxy\FGVC-PIM-master\dataset\test1 data_size: 448 num_workers: 2 batch_size: 8 model_name: efficient pretrained: ~ optimizer: SGD max_lr: 0.0005 wdecay: 0.0005 max_epochs: 300 warmup_batchs: 800 use_amp: True use_fpn: True fpn_size: 1536 use_selection: True num_classes: 25 num_selects: layer1: 2048 layer2: 512 layer3: 128 layer4: 32 use_combiner: False lambda_b: 0.5 lambda_s: 0.0 lambda_n: 5.0 lambda_c: 1.0 update_freq: 2 log_freq: 100 eval_freq: 2

did you solve this issue

9vvqaq commented 1 month ago

Solved it！ change the select layers is OK,i am just a freshman hope i can help you

9vvqaq commented 1 month ago

use 323232 is OK

How is your config file set?

project_name: tea_swin_t exp_name: T3000 use_wandb: True wandb_entity: dechenzhu train_root: D:\hxy\FGVC-PIM-master\dataset\data3 val_root: D:\hxy\FGVC-PIM-master\dataset\test1 data_size: 448 num_workers: 2 batch_size: 8 model_name: efficient pretrained: ~ optimizer: SGD max_lr: 0.0005 wdecay: 0.0005 max_epochs: 300 warmup_batchs: 800 use_amp: True use_fpn: True fpn_size: 1536 use_selection: True num_classes: 25 num_selects: layer1: 2048 layer2: 512 layer3: 128 layer4: 32 use_combiner: False lambda_b: 0.5 lambda_s: 0.0 lambda_n: 5.0 lambda_c: 1.0 update_freq: 2 log_freq: 100 eval_freq: 2

did you solve this issue