Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+rtdetr_msda.axmodel filter=lfs diff=lfs merge=lfs -text
+ssd_horse.jpg filter=lfs diff=lfs merge=lfs -text

axmodel_inference.py

@@ -0,0 +1,135 @@
+# import onnxruntime
+import axengine as axe
+
+CLASS_NAMES = [
+    "person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light",
+    "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow",
+    "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee",
+    "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard",
+    "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple",
+    "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch",
+    "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone",
+    "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear",
+    "hair drier", "toothbrush"]
+
+
+class axmodel_inferencer:
+
+    def __init__(self, model_path) -> None:
+        # self.onnx_model_sess = onnxruntime.InferenceSession(model_path)
+        self.onnx_model_sess = axe.InferenceSession(model_path)
+        self.output_names = []
+        self.input_names = []
+        print(model_path)
+        for i in range(len(self.onnx_model_sess.get_inputs())):
+            self.input_names.append(self.onnx_model_sess.get_inputs()[i].name)
+            print("    input:", i,
+                  self.onnx_model_sess.get_inputs()[i].name,
+                  self.onnx_model_sess.get_inputs()[i].shape)
+
+        for i in range(len(self.onnx_model_sess.get_outputs())):
+            self.output_names.append(
+                self.onnx_model_sess.get_outputs()[i].name)
+            print("    output:", i,
+                  self.onnx_model_sess.get_outputs()[i].name,
+                  self.onnx_model_sess.get_outputs()[i].shape)
+        print("")
+
+    def get_input_count(self):
+        return len(self.input_names)
+
+    def get_input_shape(self, idx: int):
+        return self.onnx_model_sess.get_inputs()[idx].shape
+
+    def get_input_names(self):
+        return self.input_names
+
+    def get_output_count(self):
+        return len(self.output_names)
+
+    def get_output_shape(self, idx: int):
+        return self.onnx_model_sess.get_outputs()[idx].shape
+
+    def get_output_names(self):
+        return self.output_names
+
+    def inference(self, tensor):
+        return self.onnx_model_sess.run(
+            self.output_names, input_feed={self.input_names[0]: tensor})
+
+    def inference_multi_input(self, tensors: list):
+        inputs = dict()
+        for idx, tensor in enumerate(tensors):
+            inputs[self.input_names[idx]] = tensor
+        return self.onnx_model_sess.run(input_feed=inputs)
+    
+    def numpy_sigmoid(self,x):
+        """
+        用NumPy实现的sigmoid函数
+        
+        参数:
+        x (np.ndarray): 输入数组
+        
+        返回:
+        np.ndarray: 经过sigmoid处理后的数组
+        """
+        return 1 / (1 + np.exp(-x))
+    
+
+
+
+if __name__ == "__main__":
+    axmodel_model_path = "rtdetr_msda.axmodel"
+    test_model = axmodel_inferencer(axmodel_model_path)
+
+        # import onnxruntime as ort 
+    from PIL import Image, ImageDraw
+    # from torchvision.transforms import ToTensor
+    import numpy as np
+    # import torch
+
+    # # print(onnx.helper.printable_graph(mm.graph))
+
+
+    image = Image.open('ssd_horse.jpg').convert('RGB')
+    im = image.resize((640, 640))
+    im_data = np.array([im])
+    print(im_data.shape)
+
+    pred_logits,pred_boxes = test_model.inference(im_data)
+
+    pred_logits = np.array(pred_logits)
+    pred_boxes = np.array(pred_boxes)
+    print(pred_boxes.shape,pred_logits.shape)
+
+    
+    # pred_logits = 1/(1+np.exp(-pred_logits))
+
+    pred_logits = test_model.numpy_sigmoid(pred_logits)
+
+
+    # print(pred["pred_logits"].shape,pred["pred_boxes"].shape)
+    # argmax = torch.argmax(pred_logits,2).reshape(-1)
+    argmax = np.argmax(pred_logits, axis=2).reshape(-1)
+    print(argmax.shape)
+
+    # pred_logits = pred["pred_logits"]
+    # pred_boxes = pred["pred_boxes"]
+    draw = ImageDraw.Draw(image)
+
+    for i,idx in enumerate(argmax):
+        score = pred_logits[0,i,idx]
+        if score > 0.6:
+            print(score,idx)
+            bbox = pred_boxes[0,i]
+            print(bbox)
+            cx,cy,w,h = bbox
+            x0 = (cx-0.5*w)*image.width
+            y0 = (cy-0.5*h)*image.height
+            x1 = (cx+0.5*w)*image.width
+            y1 = (cy+0.5*h)*image.height
+            draw.rectangle([x0,y0,x1,y1],outline="red")
+            draw.text([x0,y0],CLASS_NAMES[idx]+" %.2f"%score)
+    image.save("output.jpg")
+    
+

requirements.txt

@@ -0,0 +1,8 @@
+torch==2.0.1
+torchvision==0.15.2
+onnx==1.14.0
+onnxruntime==1.15.1
+pycocotools
+PyYAML
+scipy
+transformers

rtdetr_msda.axmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa8573d79dff26d54eba74c6ac835296a39ef5439b365beb58578d7275b07c3
+size 22428394

rtdetr_r18vd_5x_coco_objects365_from_paddle_opt.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ffbfa35923b2d28b7764f2f8c559e4bf32ba5cbb6826c777fe63dfac632565
+size 81191543