Open Gbbfine opened 6 months ago
代码在linux服务器上能运行,但是在windows上运行不了,会报以下错误,也没有结果生成
这是代码 from mmdeploy_runtime import Segmentor import cv2 import numpy as np
img = cv2.imread('D:\Code\pycharm_work\onnx\AH2-95_crop_2_2.jpg')
segmentor = Segmentor(model_path='D:\Code\pycharm_work\onnx\segformerIMF', device_name='cpu', device_id=0)
seg = segmentor(img)
palette = np.random.randint(0, 256, size=(256, 3)) color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8) for label, color in enumerate(palette): color_seg[seg == label, :] = color
color_seg = color_seg[..., ::-1] img = img 0.5 + color_seg 0.5 img = img.astype(np.uint8) cv2.imwrite('output_segmentation.png', img)
这是报错 C:\Users\GBB.conda\envs\pytorch\python.exe D:\Code\pycharm_work\onnx\main.py loading mmdeploy_ort_net.dll ... [2024-04-25 23:28:33.368] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "D:\Code\pycharm_work\onnx\segformerIMF" [2024-04-25 23:28:33.434] [mmdeploy] [error] [ort_net.cpp:205] unhandled exception when creating ORTNet: Failed to load model because protobuf parsing failed. [2024-04-25 23:28:33.434] [mmdeploy] [error] [net_module.cpp:54] Failed to create Net backend: onnxruntime, config: { "context": { "device": "", "model": "", "stream": "" }, "input": [ "prep_output" ], "input_map": { "img": "input" }, "is_batched": true, "module": "Net", "name": "segformer", "output": [ "infer_output" ], "output_map": {}, "type": "Task" } [2024-04-25 23:28:33.434] [mmdeploy] [error] [task.cpp:99] error parsing config: { "context": { "device": "", "model": "", "stream": "" }, "input": [ "prep_output" ], "input_map": { "img": "input" }, "is_batched": true, "module": "Net", "name": "segformer", "output": [ "infer_output" ], "output_map": {}, "type": "Task" }
Process finished with exit code -1073741819 (0xC0000005)
1
请问你解决了吗?我也遇到了这个问题。
Checklist
Describe the bug
代码在linux服务器上能运行,但是在windows上运行不了,会报以下错误,也没有结果生成
这是代码 from mmdeploy_runtime import Segmentor import cv2 import numpy as np
img = cv2.imread('D:\Code\pycharm_work\onnx\AH2-95_crop_2_2.jpg')
create a classifier
segmentor = Segmentor(model_path='D:\Code\pycharm_work\onnx\segformerIMF', device_name='cpu', device_id=0)
perform inference
seg = segmentor(img)
visualize inference result
random a palette with size 256x3
palette = np.random.randint(0, 256, size=(256, 3)) color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8) for label, color in enumerate(palette): color_seg[seg == label, :] = color
convert to BGR
color_seg = color_seg[..., ::-1] img = img 0.5 + color_seg 0.5 img = img.astype(np.uint8) cv2.imwrite('output_segmentation.png', img)
这是报错 C:\Users\GBB.conda\envs\pytorch\python.exe D:\Code\pycharm_work\onnx\main.py loading mmdeploy_ort_net.dll ... [2024-04-25 23:28:33.368] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "D:\Code\pycharm_work\onnx\segformerIMF" [2024-04-25 23:28:33.434] [mmdeploy] [error] [ort_net.cpp:205] unhandled exception when creating ORTNet: Failed to load model because protobuf parsing failed. [2024-04-25 23:28:33.434] [mmdeploy] [error] [net_module.cpp:54] Failed to create Net backend: onnxruntime, config: { "context": { "device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": true,
"module": "Net",
"name": "segformer",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
[2024-04-25 23:28:33.434] [mmdeploy] [error] [task.cpp:99] error parsing config: {
"context": {
"device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": true,
"module": "Net",
"name": "segformer",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
Process finished with exit code -1073741819 (0xC0000005)
Reproduction
1
Environment
Error traceback