djl
djl copied to clipboard
Published
20 hours ago •
deepjavalibrary
deepjavalibrary
YOLOv7 using PyTorch Engine: Failed to load PyTorch native library
I am trying to use YOLOv7 with PyTorch but I receive the error Failed to load PyTorch native library.
I am running this on windows 10 with the following libraries:
api-0.21.0.jar
commons-compress-1.22.jar
pytorch-engine-0.21.0.jar
pytorch-jni-1.13.1-0.21.0.jar
pytorch-model-zoo-0.21.0.jar
pytorch-native-cpu-1.13.1.jar
pytorch-native-cpu-1.13.1-win-x86_64.jar
slf4j-api-2.0.6.jar
slf4j-simple-2.0.6.jar
My code:
public class YoloNet {
Predictor<Image, DetectedObjects> predictor;
public YoloNet() {
int imageSize = 640;
Pipeline pipeline = new Pipeline();
pipeline.add(new Resize(imageSize));
pipeline.add(new ToTensor());
List<String> synset = new ArrayList<>(0);
try {
synset = Files.readAllLines(Paths.get("coco.names"));
} catch (IOException e) {
System.err.println("Could not read names file!");
e.printStackTrace();
}
Translator<Image, DetectedObjects> translator = YoloTranslator
.builder()
.setPipeline(pipeline)
.optSynset(synset)
.optThreshold(0.4f)
.addTransform(new Resize(640))
.build();
Criteria<Image, DetectedObjects> criteria =
Criteria.builder()
.optApplication(Application.CV.OBJECT_DETECTION)
.setTypes(Image.class, DetectedObjects.class)
.optModelPath(Paths.get("yolov7.pt"))
.optTranslator(translator)
.optEngine("PyTorch")
.optProgress(new ProgressBar())
.build();
try (ZooModel<Image, DetectedObjects> model = criteria.loadModel()) {
predictor = model.newPredictor();
} catch (ModelNotFoundException | MalformedModelException | IOException e) {
throw new RuntimeException(e);
}
}
public void detect(Image image) {
try {
DetectedObjects detection = predictor.predict(image);
System.out.println(detection);
} catch (TranslateException e) {
throw new RuntimeException(e);
}
}
}
criteria.loadModel() crashes with error output:
[main] WARN ai.djl.repository.SimpleRepository - Simple repository pointing to a non-archive file.
Loading: 100% |========================================|
Exception in thread "main" ai.djl.engine.EngineException: Failed to load PyTorch native library
at ai.djl.pytorch.engine.PtEngine.newInstance(PtEngine.java:84)
at ai.djl.pytorch.engine.PtEngineProvider.getEngine(PtEngineProvider.java:40)
at ai.djl.engine.Engine.getEngine(Engine.java:187)
at ai.djl.Model.newInstance(Model.java:99)
at ai.djl.repository.zoo.BaseModelLoader.createModel(BaseModelLoader.java:191)
at ai.djl.repository.zoo.BaseModelLoader.loadModel(BaseModelLoader.java:154)
at ai.djl.repository.zoo.Criteria.loadModel(Criteria.java:172)
at YoloNet.<init>(YoloNet.java:61)
at YOLO.<init>(YOLO.java:105)
at YOLO.main(YOLO.java:145)
Caused by: java.lang.NoClassDefFoundError: com/sun/jna/Library
at java.base/java.lang.ClassLoader.defineClass1(Native Method)
at java.base/java.lang.ClassLoader.defineClass(ClassLoader.java:1016)
at java.base/java.security.SecureClassLoader.defineClass(SecureClassLoader.java:174)
at java.base/jdk.internal.loader.BuiltinClassLoader.defineClass(BuiltinClassLoader.java:800)
at java.base/jdk.internal.loader.BuiltinClassLoader.findClassOnClassPathOrNull(BuiltinClassLoader.java:698)
at java.base/jdk.internal.loader.BuiltinClassLoader.loadClassOrNull(BuiltinClassLoader.java:621)
at java.base/jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:579)
at java.base/jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:178)
at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:521)
at ai.djl.util.cuda.CudaUtils.loadLibrary(CudaUtils.java:179)
at ai.djl.util.cuda.CudaUtils.<clinit>(CudaUtils.java:33)
at ai.djl.util.Platform.fromSystem(Platform.java:188)
at ai.djl.util.Platform.fromSystem(Platform.java:148)
at ai.djl.util.Platform.detectPlatform(Platform.java:68)
at ai.djl.pytorch.jni.LibUtils.findNativeLibrary(LibUtils.java:274)
at ai.djl.pytorch.jni.LibUtils.getLibTorch(LibUtils.java:89)
at ai.djl.pytorch.jni.LibUtils.loadLibrary(LibUtils.java:77)
at ai.djl.pytorch.engine.PtEngine.newInstance(PtEngine.java:53)
... 9 more
Caused by: java.lang.ClassNotFoundException: com.sun.jna.Library
at java.base/jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:581)
at java.base/jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:178)
at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:521)
... 27 more
You didn't include JNA in your classpath.
I suggest you use a proper build system (e.g. maven or gradle) to build your project.
I have switched to maven using these dependencies:
<dependency>
<groupId>ai.djl</groupId>
<artifactId>api</artifactId>
<version>0.21.0</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-engine</artifactId>
<version>0.21.0</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-simple</artifactId>
<version>2.0.6</version>
</dependency>
Now I get:
Exception in thread "main" ai.djl.engine.EngineException: PytorchStreamReader failed locating file constants.pkl: file not found
at ai.djl.pytorch.jni.PyTorchLibrary.moduleLoad(Native Method)
at ai.djl.pytorch.jni.JniUtils.loadModule(JniUtils.java:1661)
at ai.djl.pytorch.engine.PtModel.load(PtModel.java:92)
at ai.djl.repository.zoo.BaseModelLoader.loadModel(BaseModelLoader.java:161)
at ai.djl.repository.zoo.Criteria.loadModel(Criteria.java:172)
at YoloNet.<init>(YoloNet.java:60)
at YOLO.<init>(YOLO.java:106)
at YOLO.main(YOLO.java:146)
You need use jit trace to trace your model, see: https://docs.djl.ai/master/docs/pytorch/how_to_convert_your_model_to_torchscript.html
For yolo model, you'd better use yolo provided tool to export model to torchscript model.
Can you use yolov5, we have yolov5s in our model zoo (PyTorch and onnx). You can use them directly.
I exported the model to torchscript and criteria.loadModel() is now working but now when I run predictor.predict(image) I get a new exception:
java.lang.RuntimeException: ai.djl.translate.TranslateException: ai.djl.engine.EngineException: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File "code/__torch__/models/yolo.py", line 221, in forward
model104 = self.model
_0 = getattr(model104, "0")
_106 = (_2).forward((_1).forward((_0).forward(x, ), ), )
~~~~~~~~~~~ <--- HERE
_107 = (_3).forward(_106, )
_108 = (_4).forward(_107, )
File "code/__torch__/models/common.py", line 12, in forward
act = self.act
conv = self.conv
_0 = (act).forward((conv).forward(x, ), )
~~~~~~~~~~~~~ <--- HERE
return _0
class Concat(Module):
File "code/__torch__/torch/nn/modules/conv.py", line 12, in forward
bias = self.bias
weight = self.weight
x0 = torch._convolution(x, weight, bias, [1, 1], [1, 1], [1, 1], False, [0, 0], 1, False, False, True, True)
~~~~~~~~~~~~~~~~~~ <--- HERE
return x0
Traceback of TorchScript, original code (most recent call last):
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/conv.py(459): _conv_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/conv.py(463): forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/content/yolov7/models/common.py(111): fuseforward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/content/yolov7/models/yolo.py(625): forward_once
/content/yolov7/models/yolo.py(599): forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/usr/local/lib/python3.9/dist-packages/torch/jit/_trace.py(976): trace_module
/usr/local/lib/python3.9/dist-packages/torch/jit/_trace.py(759): trace
/content/yolov7/export.py(77): <module>
RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[1, 640, 640, 640] to have 3 channels, but got 640 channels instead
at YoloNet.detect(YoloNet.java:94)
at YOLO$1.drop(YOLO.java:135)
at java.desktop/sun.awt.dnd.SunDropTargetContextPeer.processDropMessage(SunDropTargetContextPeer.java:547)
at java.desktop/sun.awt.dnd.SunDropTargetContextPeer$EventDispatcher.dispatchDropEvent(SunDropTargetContextPeer.java:863)
at java.desktop/sun.awt.dnd.SunDropTargetContextPeer$EventDispatcher.dispatchEvent(SunDropTargetContextPeer.java:787)
at java.desktop/sun.awt.dnd.SunDropTargetEvent.dispatch(SunDropTargetEvent.java:48)
at java.desktop/java.awt.Component.dispatchEventImpl(Component.java:4876)
at java.desktop/java.awt.Container.dispatchEventImpl(Container.java:2321)
at java.desktop/java.awt.Component.dispatchEvent(Component.java:4843)
at java.desktop/java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4918)
at java.desktop/java.awt.LightweightDispatcher.processDropTargetEvent(Container.java:4621)
at java.desktop/java.awt.LightweightDispatcher.dispatchEvent(Container.java:4483)
at java.desktop/java.awt.Container.dispatchEventImpl(Container.java:2307)
at java.desktop/java.awt.Window.dispatchEventImpl(Window.java:2772)
at java.desktop/java.awt.Component.dispatchEvent(Component.java:4843)
at java.desktop/java.awt.EventQueue.dispatchEventImpl(EventQueue.java:772)
at java.desktop/java.awt.EventQueue$4.run(EventQueue.java:721)
at java.desktop/java.awt.EventQueue$4.run(EventQueue.java:715)
at java.base/java.security.AccessController.doPrivileged(Native Method)
at java.base/java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:85)
at java.base/java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:95)
at java.desktop/java.awt.EventQueue$5.run(EventQueue.java:745)
at java.desktop/java.awt.EventQueue$5.run(EventQueue.java:743)
at java.base/java.security.AccessController.doPrivileged(Native Method)
at java.base/java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:85)
at java.desktop/java.awt.EventQueue.dispatchEvent(EventQueue.java:742)
at java.desktop/java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:203)
at java.desktop/java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:124)
at java.desktop/java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:113)
at java.desktop/java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:109)
at java.desktop/java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:101)
at java.desktop/java.awt.EventDispatchThread.run(EventDispatchThread.java:90)
Caused by: ai.djl.translate.TranslateException: ai.djl.engine.EngineException: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File "code/__torch__/models/yolo.py", line 221, in forward
model104 = self.model
_0 = getattr(model104, "0")
_106 = (_2).forward((_1).forward((_0).forward(x, ), ), )
~~~~~~~~~~~ <--- HERE
_107 = (_3).forward(_106, )
_108 = (_4).forward(_107, )
File "code/__torch__/models/common.py", line 12, in forward
act = self.act
conv = self.conv
_0 = (act).forward((conv).forward(x, ), )
~~~~~~~~~~~~~ <--- HERE
return _0
class Concat(Module):
File "code/__torch__/torch/nn/modules/conv.py", line 12, in forward
bias = self.bias
weight = self.weight
x0 = torch._convolution(x, weight, bias, [1, 1], [1, 1], [1, 1], False, [0, 0], 1, False, False, True, True)
~~~~~~~~~~~~~~~~~~ <--- HERE
return x0
Traceback of TorchScript, original code (most recent call last):
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/conv.py(459): _conv_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/conv.py(463): forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/content/yolov7/models/common.py(111): fuseforward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/content/yolov7/models/yolo.py(625): forward_once
/content/yolov7/models/yolo.py(599): forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/usr/local/lib/python3.9/dist-packages/torch/jit/_trace.py(976): trace_module
/usr/local/lib/python3.9/dist-packages/torch/jit/_trace.py(759): trace
/content/yolov7/export.py(77): <module>
RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[1, 640, 640, 640] to have 3 channels, but got 640 channels instead
at ai.djl.inference.Predictor.batchPredict(Predictor.java:189)
at ai.djl.inference.Predictor.predict(Predictor.java:126)
at YoloNet.detect(YoloNet.java:91)
... 31 more
Caused by: ai.djl.engine.EngineException: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File "code/__torch__/models/yolo.py", line 221, in forward
model104 = self.model
_0 = getattr(model104, "0")
_106 = (_2).forward((_1).forward((_0).forward(x, ), ), )
~~~~~~~~~~~ <--- HERE
_107 = (_3).forward(_106, )
_108 = (_4).forward(_107, )
File "code/__torch__/models/common.py", line 12, in forward
act = self.act
conv = self.conv
_0 = (act).forward((conv).forward(x, ), )
~~~~~~~~~~~~~ <--- HERE
return _0
class Concat(Module):
File "code/__torch__/torch/nn/modules/conv.py", line 12, in forward
bias = self.bias
weight = self.weight
x0 = torch._convolution(x, weight, bias, [1, 1], [1, 1], [1, 1], False, [0, 0], 1, False, False, True, True)
~~~~~~~~~~~~~~~~~~ <--- HERE
return x0
Traceback of TorchScript, original code (most recent call last):
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/conv.py(459): _conv_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/conv.py(463): forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/content/yolov7/models/common.py(111): fuseforward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/content/yolov7/models/yolo.py(625): forward_once
/content/yolov7/models/yolo.py(599): forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1182): _slow_forward
/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py(1194): _call_impl
/usr/local/lib/python3.9/dist-packages/torch/jit/_trace.py(976): trace_module
/usr/local/lib/python3.9/dist-packages/torch/jit/_trace.py(759): trace
/content/yolov7/export.py(77): <module>
RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[1, 640, 640, 640] to have 3 channels, but got 640 channels instead
at ai.djl.pytorch.jni.PyTorchLibrary.moduleRunMethod(Native Method)
at ai.djl.pytorch.jni.IValueUtils.forward(IValueUtils.java:53)
at ai.djl.pytorch.engine.PtSymbolBlock.forwardInternal(PtSymbolBlock.java:145)
at ai.djl.nn.AbstractBaseBlock.forward(AbstractBaseBlock.java:79)
at ai.djl.nn.Block.forward(Block.java:127)
at ai.djl.inference.Predictor.predictInternal(Predictor.java:140)
at ai.djl.inference.Predictor.batchPredict(Predictor.java:180)
... 33 more
removing .addTransform(new Resize(640)) from the translator fixed the issue but now I get:
java.lang.RuntimeException: ai.djl.translate.TranslateException: java.lang.IndexOutOfBoundsException: Index 96 out of bounds for length 80
at YoloNet.detect(YoloNet.java:94)
at YOLO$1.drop(YOLO.java:135)
at java.desktop/sun.awt.dnd.SunDropTargetContextPeer.processDropMessage(SunDropTargetContextPeer.java:547)
at java.desktop/sun.awt.dnd.SunDropTargetContextPeer$EventDispatcher.dispatchDropEvent(SunDropTargetContextPeer.java:863)
at java.desktop/sun.awt.dnd.SunDropTargetContextPeer$EventDispatcher.dispatchEvent(SunDropTargetContextPeer.java:787)
at java.desktop/sun.awt.dnd.SunDropTargetEvent.dispatch(SunDropTargetEvent.java:48)
at java.desktop/java.awt.Component.dispatchEventImpl(Component.java:4876)
at java.desktop/java.awt.Container.dispatchEventImpl(Container.java:2321)
at java.desktop/java.awt.Component.dispatchEvent(Component.java:4843)
at java.desktop/java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4918)
at java.desktop/java.awt.LightweightDispatcher.processDropTargetEvent(Container.java:4621)
at java.desktop/java.awt.LightweightDispatcher.dispatchEvent(Container.java:4483)
at java.desktop/java.awt.Container.dispatchEventImpl(Container.java:2307)
at java.desktop/java.awt.Window.dispatchEventImpl(Window.java:2772)
at java.desktop/java.awt.Component.dispatchEvent(Component.java:4843)
at java.desktop/java.awt.EventQueue.dispatchEventImpl(EventQueue.java:772)
at java.desktop/java.awt.EventQueue$4.run(EventQueue.java:721)
at java.desktop/java.awt.EventQueue$4.run(EventQueue.java:715)
at java.base/java.security.AccessController.doPrivileged(Native Method)
at java.base/java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:85)
at java.base/java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:95)
at java.desktop/java.awt.EventQueue$5.run(EventQueue.java:745)
at java.desktop/java.awt.EventQueue$5.run(EventQueue.java:743)
at java.base/java.security.AccessController.doPrivileged(Native Method)
at java.base/java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:85)
at java.desktop/java.awt.EventQueue.dispatchEvent(EventQueue.java:742)
at java.desktop/java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:203)
at java.desktop/java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:124)
at java.desktop/java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:113)
at java.desktop/java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:109)
at java.desktop/java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:101)
at java.desktop/java.awt.EventDispatchThread.run(EventDispatchThread.java:90)
Caused by: ai.djl.translate.TranslateException: java.lang.IndexOutOfBoundsException: Index 96 out of bounds for length 80
at ai.djl.inference.Predictor.batchPredict(Predictor.java:189)
at ai.djl.inference.Predictor.predict(Predictor.java:126)
at YoloNet.detect(YoloNet.java:91)
... 31 more
Caused by: java.lang.IndexOutOfBoundsException: Index 96 out of bounds for length 80
at java.base/jdk.internal.util.Preconditions.outOfBounds(Preconditions.java:64)
at java.base/jdk.internal.util.Preconditions.outOfBoundsCheckIndex(Preconditions.java:70)
at java.base/jdk.internal.util.Preconditions.checkIndex(Preconditions.java:248)
at java.base/java.util.Objects.checkIndex(Objects.java:372)
at java.base/java.util.ArrayList.get(ArrayList.java:459)
at ai.djl.modality.cv.translator.YoloTranslator.processOutput(YoloTranslator.java:64)
at ai.djl.modality.cv.translator.YoloTranslator.processOutput(YoloTranslator.java:28)
at ai.djl.inference.Predictor.processOutputs(Predictor.java:225)
at ai.djl.inference.Predictor.batchPredict(Predictor.java:183)
... 33 more
Looks like it is expecting the synset to have 96 items but the model is the default example and it only has 80 classes.
When you load the Model, you will need to provide the list of available classes to your translator. You can use the method .optSynset(...) or .optSynsetUrl(...) on the YoloTranslator.Builder to do this
I'm setting the .optSynset(...), I posted my code in the first comment. I tried re-exporting to torchscript using different export settings and it changed to IndexOutOfBoundsException for 2102 out of 2100, so it appears to have something to do witth my export settings but I dont know what export settings to use.
`public static DetectedObjects predict() throws IOException { Path imageFile = Paths.get("/Users/iotinall/Desktop/LHQJW/K44464075_1_20230605T121021Z.jpg"); Image img = ImageFactory.getInstance().fromFile(imageFile); Criteria<Image, DetectedObjects> criteria=Criteria.builder() .setTypes(Image.class,DetectedObjects.class) .optModelPath(Paths.get("/Users/iotinall/Desktop/torchmodel")) .optModelName("best.torchscript.pt") .optTranslatorFactory( new YoloTranslatorFactory()) .optEngine("PyTorch") .build();
try (ZooModel<Image, DetectedObjects> model = criteria.loadModel()) {
try (Predictor<Image, DetectedObjects> predictor = model.newPredictor()) {
DetectedObjects detection = predictor.predict(img);
saveBoundingBoxImage(img, detection);
return detection;
} catch (TranslateException e) {
throw new RuntimeException(e);
}
} catch (ModelNotFoundException e) {
throw new RuntimeException(e);
} catch (MalformedModelException e) {
throw new RuntimeException(e);
}
}`
I use the djl to load the pytorch torchscript model ,the synset.txt content is :
now I run the program ,get the error
We didn't test YoloTranslator with yolov7, there might some difference in yolov7 output tensor layout.
Do you know what's the model's expected image size?
We didn't test
YoloTranslatorwith yolov7, there might some difference in yolov7 output tensor layout.Do you know what's the model's expected image size?
When I trained the model, I set the image size to 800 * 800
You didn't set image size in your Translator, the default will be resize to 224 x 224
You didn't set image size in your Translator, the default will be resize to 224 x 224
After setting the image size, the program now reports an error
How many classes when you train your model? The number of classes in synset must match to classes in your training
How many classes when you train your model? The number of classes in synset must match to classes in your training
three number of classes
closing old issues. Feel free to open an new issue if you have questions.