added tf_model

README.md

@@ -3,7 +3,7 @@ license: apache-2.0
 ---
 MobileNet V2 model from Torchvision fine-tuned for Imagenette dataset. Checkpoint trained for 100 epoches using https://github.com/alexsu52/mobilenet_v2_imagenette.
 
-Top-1 accuracy is 87.61%.
+Top-1 accuracy is 98.64%.
 
 The main intent is to use it in samples and demos for model optimization. Here is the advantages:
 - Imagenette can automatically downloaded and is quite small.
@@ -22,4 +22,4 @@ model = models.mobilenet_v2(num_classes=IMAGENETTE_CLASSES)
         
 checkpoint = torch.hub.load_state_dict_from_url(CHECKPOINT_URL, progress=False)
 model.load_state_dict(checkpoint['state_dict'])
-```
+```

mobilenet_v2_imagenette.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eae737121b40459c2511d16b14a3278588c1bb82d95ae8a6a0f8f6c20fa6db8
-size 9453491
+oid sha256:c6eab06589151102f6a0270bf860d08098a028f9849b9c628aa3d0c67f20235f
+size 9456587

openvino_model.tgz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34170d1e45d446f492bf058e6fe0519a834aa75f3fd1d4e259e95c9659aff8f2
-size 8239224
+oid sha256:23ca9dfc28c2cda58bf8219fcdd5204feb7b33777f71ac87c42c0dc639bf16a0
+size 8258642

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830796ef9827f8ea238e1b06eb1c2c23e2a3d4c849888d810afb556257f0146c
-size 18169423
+oid sha256:32971bd064c48216991208b4dbabd0b2065ab003d2a0cec1f1a4cf3cb3d25ad2
+size 18172593

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21120928145ffebbdc7629daa5ea04026ab52d7236008bc0ba908ad1a4ebe97
+size 9476336