RWKV-6 模型转换报错 The input tensor cannot be reshaped to the requested shape. Input shape:{1,2048,1,1}, requested shape:{1,32,64,64} (rknn-toolkit2 v2.2.0)

[happyme531]

模型和转换脚本和 #168 中的相同，toolkit2版本升级到v2.2.0之后又开始报另一个错误：

...
D     convert_exmatmul_to_conv: remove node = ['/blocks.23/ffn_key/MatMul'], add node = ['/blocks.23/ffn_key/MatMul']
D     convert_exmatmul_to_conv: remove node = ['/head/MatMul'], add node = ['/head/MatMul']
D     fold_constant ...
I        FoldConstant :   0%|                                              | 0/1885 [00:00<?, ?it/s]2024-10-09 20:55:45.093023561 [E:onnxruntime:, sequential_executor.cc:514 ExecuteKernel] Non-zero status code returned while running Reshape node. Name:'/blocks.0/MatMul_4_output_0_mm-rs' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{1,2048,1,1}, requested shape:{1,32,64,64}

I        FoldConstant :   2%|▊                                   | 40/1885 [00:00<00:04, 429.97it/s]
E build: Traceback (most recent call last):
  File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
  File "rknn/api/rknn_base.py", line 1936, in rknn.api.rknn_base.RKNNBase.build
  File "rknn/api/graph_optimizer.py", line 2204, in rknn.api.graph_optimizer.GraphOptimizer.fuse_ops
  File "rknn/api/graph_optimizer.py", line 976, in rknn.api.graph_optimizer.GraphOptimizer.fold_constant
  File "rknn/api/session.py", line 150, in rknn.api.session.Session.run
  File "/home/zt/.conda/envs/rknn/lib/python3.8/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'/blocks.0/MatMul_4_output_0_mm-rs' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{1,2048,1,1}, requested shape:{1,32,64,64}


W build: ===================== WARN(11) =====================
E rknn-toolkit2 version: 2.2.0
Traceback (most recent call last):
  File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
  File "rknn/api/rknn_base.py", line 1936, in rknn.api.rknn_base.RKNNBase.build
  File "rknn/api/graph_optimizer.py", line 2204, in rknn.api.graph_optimizer.GraphOptimizer.fuse_ops
  File "rknn/api/graph_optimizer.py", line 976, in rknn.api.graph_optimizer.GraphOptimizer.fold_constant
  File "rknn/api/session.py", line 150, in rknn.api.session.Session.run
  File "/home/zt/.conda/envs/rknn/lib/python3.8/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'/blocks.0/MatMul_4_output_0_mm-rs' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{1,2048,1,1}, requested shape:{1,32,64,64}


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "./convert_rknn.py", line 47, in <module>
    ret = rknn.build(do_quantization=QUANTIZE, dataset=DATASET, rknn_batch_size=None)
  File "/home/zt/.conda/envs/rknn/lib/python3.8/site-packages/rknn/api/rknn.py", line 192, in build
    return self.rknn_base.build(do_quantization=do_quantization, dataset=dataset, expand_batch_size=rknn_batch_size)
  File "rknn/api/rknn_log.py", line 314, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
  File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e
ValueError: Traceback (most recent call last):
  File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
  File "rknn/api/rknn_base.py", line 1936, in rknn.api.rknn_base.RKNNBase.build
  File "rknn/api/graph_optimizer.py", line 2204, in rknn.api.graph_optimizer.GraphOptimizer.fuse_ops
  File "rknn/api/graph_optimizer.py", line 976, in rknn.api.graph_optimizer.GraphOptimizer.fold_constant
  File "rknn/api/session.py", line 150, in rknn.api.session.Session.run
  File "/home/zt/.conda/envs/rknn/lib/python3.8/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'/blocks.0/MatMul_4_output_0_mm-rs' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{1,2048,1,1}, requested shape:{1,32,64,64}

看起来是图优化器的问题。

[zen-xingle]

是的，这个问题看起来是图优化导致的异常。从log无法判断具体的错误代码，需要有模型复现才比较好定位修复了

[happyme531]

是的，这个问题看起来是图优化导致的异常。从log无法判断具体的错误代码，需要有模型复现才比较好定位修复了

拿这个不带权重的模型试试? 权重太大没上传 https://github.com/user-attachments/files/17308486/check0_base_optimize.onnx.zip