Closed
Description
I have similar problem with #763 when trying to adopt Citrinet-Example.ipynb.
My model is a fine-tuned Citrinet512 from NeMo.
By the way, my pytorch_tensorrt version is 1.3.0.
Here is my code:
import torch
import torch.nn as nn
import torch_tensorrt as torchtrt
import argparse
precisions = [torch.float, torch.half]
batch_sizes = [1,8,32,128]
model = torch.jit.load(model_path+f"{variant}.ts")
model.eval()
for precision in precisions:
for batch_size in batch_sizes:
compile_settings = {
"inputs": [torchtrt.Input(shape=[batch_size, 80, 1488], dtype=torch.int), torchtrt.Input(shape=[1, batch_size], dtype=torch.int)],
"enabled_precisions": {precision},
"workspace_size": 2000000000,
"truncate_long_and_double": True,
}
print(f"Generating Torchscript-TensorRT module for batchsize {batch_size} precision {precision}")
trt_ts_module = torchtrt.compile(model, **compile_settings)
torch.jit.save(trt_ts_module, f"{variant}_bs{batch_size}_{precision}.torch-tensorrt")Output:
RuntimeError Traceback (most recent call last)
Input In [6], in <module>
14 compile_settings = {
15 "inputs": [torchtrt.Input(shape=[batch_size, 80, 1488], dtype=torch.int), torchtrt.Input(shape=[1, batch_size], dtype=torch.int)],
16 "enabled_precisions": {precision},
17 "workspace_size": 2000000000,
18 "truncate_long_and_double": True,
19 }
20 print(f"Generating Torchscript-TensorRT module for batchsize {batch_size} precision {precision}")
---> 21 trt_ts_module = torchtrt.compile(model, **compile_settings)
22 torch.jit.save(trt_ts_module, f"{variant}_bs{batch_size}_{precision}.torch-tensorrt")
File ~/nvidia-nemo-asr-training/venv/lib/python3.9/site-packages/torch_tensorrt/_compile.py:125, in compile(module, ir, inputs, enabled_precisions, **kwargs)
120 logging.log(
121 logging.Level.Info,
122 "Module was provided as a torch.nn.Module, trying to script the module with torch.jit.script. In the event of a failure please preconvert your module to TorchScript",
123 )
124 ts_mod = torch.jit.script(module)
--> 125 return torch_tensorrt.ts.compile(
126 ts_mod, inputs=inputs, enabled_precisions=enabled_precisions, **kwargs
127 )
128 elif target_ir == _IRType.fx:
129 if (
130 torch.float16 in enabled_precisions
131 or torch_tensorrt.dtype.half in enabled_precisions
132 ):
File ~/nvidia-nemo-asr-training/venv/lib/python3.9/site-packages/torch_tensorrt/ts/_compiler.py:136, in compile(module, inputs, input_signature, device, disable_tf32, sparse_weights, enabled_precisions, refit, debug, capability, num_avg_timing_iters, workspace_size, dla_sram_size, dla_local_dram_size, dla_global_dram_size, calibrator, truncate_long_and_double, require_full_compilation, min_block_size, torch_executed_ops, torch_executed_modules)
110 raise ValueError(
111 f"require_full_compilation is enabled however the list of modules and ops to run in torch is not empty. Found: torch_executed_ops: {torch_executed_ops}, torch_executed_modules: {torch_executed_modules}"
112 )
114 spec = {
115 "inputs": inputs,
116 "input_signature": input_signature,
(...)
133 },
134 }
--> 136 compiled_cpp_mod = _C.compile_graph(module._c, _parse_compile_spec(spec))
137 compiled_module = torch.jit._recursive.wrap_cpp_module(compiled_cpp_mod)
138 return compiled_module
RuntimeError: [Error thrown at core/conversion/converters/impl/conv_deconv.cpp:129] Expected orig_dims.nbDims > 2 to be true but got false
Unable to create convolution layer from node: %18096 : Tensor = aten::_convolution(%18093, %33, %32, %34, %35, %34, %18094, %18095, %30, %18094, %18094, %18094, %18094)
Originally posted by @hamjam in #763 (comment)