v0.30.2
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.30.2 for changelog.
- ConvNext-Tiny.so +0 -3
- ConvNext-Tiny_w8a16.bin +0 -3
- ConvNext-Tiny.bin → ConvNext-Tiny_w8a16.onnx +2 -2
- ConvNext-Tiny_w8a16.so +0 -3
- README.md +43 -49
ConvNext-Tiny.so
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:097d41786e182236512a87dd11cfdc77c04dd907984824718e0f94435894c766
|
| 3 |
-
size 115227224
|
|
|
|
|
|
|
|
|
|
|
|
ConvNext-Tiny_w8a16.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3e796fa66ad07cc8814e266e14fa33d472fef21781abe7da1710db292d8aa516
|
| 3 |
-
size 30827000
|
|
|
|
|
|
|
|
|
|
|
|
ConvNext-Tiny.bin → ConvNext-Tiny_w8a16.onnx
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7515e16bcb2820a207bc85359936692b3fc9a25199639c68f9950cf83d8f131
|
| 3 |
+
size 114726689
|
ConvNext-Tiny_w8a16.so
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:140ad193e8d33a7d89ef6bc325bb6dcf38ec9880f2c072852738c1162fb75c0f
|
| 3 |
-
size 30297408
|
|
|
|
|
|
|
|
|
|
|
|
README.md
CHANGED
|
@@ -35,53 +35,47 @@ More details on model performance across various devices, can be found
|
|
| 35 |
|
| 36 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
-
| ConvNext-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE |
|
| 39 |
-
| ConvNext-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.
|
| 40 |
-
| ConvNext-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.
|
| 41 |
-
| ConvNext-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 10.
|
| 42 |
-
| ConvNext-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.
|
| 43 |
-
| ConvNext-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.
|
| 44 |
-
| ConvNext-Tiny | float |
|
| 45 |
-
| ConvNext-Tiny | float |
|
| 46 |
-
| ConvNext-Tiny | float |
|
| 47 |
-
| ConvNext-Tiny | float |
|
| 48 |
-
| ConvNext-Tiny | float |
|
| 49 |
-
| ConvNext-Tiny | float |
|
| 50 |
-
| ConvNext-Tiny | float |
|
| 51 |
-
| ConvNext-Tiny | float |
|
| 52 |
-
| ConvNext-Tiny | float |
|
| 53 |
-
| ConvNext-Tiny | float |
|
| 54 |
-
| ConvNext-Tiny | float |
|
| 55 |
-
| ConvNext-Tiny | float |
|
| 56 |
-
| ConvNext-Tiny | float | Samsung Galaxy
|
| 57 |
-
| ConvNext-Tiny | float | Samsung Galaxy
|
| 58 |
-
| ConvNext-Tiny | float |
|
| 59 |
-
| ConvNext-Tiny | float |
|
| 60 |
-
| ConvNext-Tiny | float |
|
| 61 |
-
| ConvNext-Tiny | float |
|
| 62 |
-
| ConvNext-Tiny | float | Snapdragon
|
| 63 |
-
| ConvNext-Tiny |
|
| 64 |
-
| ConvNext-Tiny |
|
| 65 |
-
| ConvNext-Tiny |
|
| 66 |
-
| ConvNext-Tiny |
|
| 67 |
-
| ConvNext-Tiny | w8a16 |
|
| 68 |
-
| ConvNext-Tiny | w8a16 |
|
| 69 |
-
| ConvNext-Tiny | w8a16 |
|
| 70 |
-
| ConvNext-Tiny | w8a16 |
|
| 71 |
-
| ConvNext-Tiny | w8a16 |
|
| 72 |
-
| ConvNext-Tiny | w8a16 |
|
| 73 |
-
| ConvNext-Tiny | w8a16 |
|
| 74 |
-
| ConvNext-Tiny | w8a16 |
|
| 75 |
-
| ConvNext-Tiny | w8a16 |
|
| 76 |
-
| ConvNext-Tiny | w8a16 |
|
| 77 |
-
| ConvNext-Tiny | w8a16 |
|
| 78 |
-
| ConvNext-Tiny | w8a16 |
|
| 79 |
-
| ConvNext-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.193 ms | 0 - 67 MB | NPU | Use Export Script |
|
| 80 |
-
| ConvNext-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 65.457 ms | 214 - 551 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
| 81 |
-
| ConvNext-Tiny | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.83 ms | 0 - 57 MB | NPU | Use Export Script |
|
| 82 |
-
| ConvNext-Tiny | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 69.375 ms | 218 - 520 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
| 83 |
-
| ConvNext-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.438 ms | 0 - 0 MB | NPU | Use Export Script |
|
| 84 |
-
| ConvNext-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 88.959 ms | 199 - 199 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
| 85 |
|
| 86 |
|
| 87 |
|
|
@@ -145,8 +139,8 @@ Profiling Results
|
|
| 145 |
ConvNext-Tiny
|
| 146 |
Device : cs_8275 (ANDROID 14)
|
| 147 |
Runtime : TFLITE
|
| 148 |
-
Estimated inference time (ms) :
|
| 149 |
-
Estimated peak memory usage (MB): [0,
|
| 150 |
Total # Ops : 328
|
| 151 |
Compute Unit(s) : npu (328 ops) gpu (0 ops) cpu (0 ops)
|
| 152 |
```
|
|
|
|
| 35 |
|
| 36 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
+
| ConvNext-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.253 ms | 0 - 91 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 39 |
+
| ConvNext-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.653 ms | 1 - 10 MB | NPU | Use Export Script |
|
| 40 |
+
| ConvNext-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.11 ms | 0 - 103 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 41 |
+
| ConvNext-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 10.103 ms | 1 - 108 MB | NPU | Use Export Script |
|
| 42 |
+
| ConvNext-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.018 ms | 0 - 439 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 43 |
+
| ConvNext-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.333 ms | 1 - 3 MB | NPU | Use Export Script |
|
| 44 |
+
| ConvNext-Tiny | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.253 ms | 0 - 91 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 45 |
+
| ConvNext-Tiny | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 14.653 ms | 1 - 10 MB | NPU | Use Export Script |
|
| 46 |
+
| ConvNext-Tiny | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 3.025 ms | 0 - 442 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 47 |
+
| ConvNext-Tiny | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.349 ms | 1 - 3 MB | NPU | Use Export Script |
|
| 48 |
+
| ConvNext-Tiny | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 8.989 ms | 0 - 94 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 49 |
+
| ConvNext-Tiny | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 9.166 ms | 1 - 18 MB | NPU | Use Export Script |
|
| 50 |
+
| ConvNext-Tiny | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 3.02 ms | 0 - 438 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 51 |
+
| ConvNext-Tiny | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.328 ms | 1 - 3 MB | NPU | Use Export Script |
|
| 52 |
+
| ConvNext-Tiny | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 3.022 ms | 0 - 444 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 53 |
+
| ConvNext-Tiny | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.364 ms | 0 - 63 MB | NPU | Use Export Script |
|
| 54 |
+
| ConvNext-Tiny | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.056 ms | 0 - 189 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
|
| 55 |
+
| ConvNext-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 2.293 ms | 0 - 101 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 56 |
+
| ConvNext-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.404 ms | 0 - 100 MB | NPU | Use Export Script |
|
| 57 |
+
| ConvNext-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.231 ms | 0 - 105 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
|
| 58 |
+
| ConvNext-Tiny | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.967 ms | 0 - 95 MB | NPU | [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) |
|
| 59 |
+
| ConvNext-Tiny | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.043 ms | 0 - 96 MB | NPU | Use Export Script |
|
| 60 |
+
| ConvNext-Tiny | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.985 ms | 1 - 97 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
|
| 61 |
+
| ConvNext-Tiny | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.536 ms | 1 - 1 MB | NPU | Use Export Script |
|
| 62 |
+
| ConvNext-Tiny | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.054 ms | 57 - 57 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.onnx) |
|
| 63 |
+
| ConvNext-Tiny | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 6.86 ms | 0 - 10 MB | NPU | Use Export Script |
|
| 64 |
+
| ConvNext-Tiny | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.496 ms | 0 - 64 MB | NPU | Use Export Script |
|
| 65 |
+
| ConvNext-Tiny | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.161 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 66 |
+
| ConvNext-Tiny | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 12.758 ms | 0 - 12 MB | NPU | Use Export Script |
|
| 67 |
+
| ConvNext-Tiny | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 6.86 ms | 0 - 10 MB | NPU | Use Export Script |
|
| 68 |
+
| ConvNext-Tiny | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.175 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 69 |
+
| ConvNext-Tiny | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN | 4.794 ms | 0 - 17 MB | NPU | Use Export Script |
|
| 70 |
+
| ConvNext-Tiny | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.17 ms | 0 - 3 MB | NPU | Use Export Script |
|
| 71 |
+
| ConvNext-Tiny | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.174 ms | 0 - 15 MB | NPU | Use Export Script |
|
| 72 |
+
| ConvNext-Tiny | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 83.105 ms | 191 - 353 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
| 73 |
+
| ConvNext-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.182 ms | 0 - 66 MB | NPU | Use Export Script |
|
| 74 |
+
| ConvNext-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 78.425 ms | 431 - 764 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
| 75 |
+
| ConvNext-Tiny | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.822 ms | 0 - 59 MB | NPU | Use Export Script |
|
| 76 |
+
| ConvNext-Tiny | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 63.081 ms | 218 - 518 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
| 77 |
+
| ConvNext-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.49 ms | 0 - 0 MB | NPU | Use Export Script |
|
| 78 |
+
| ConvNext-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 87.621 ms | 228 - 228 MB | NPU | [ConvNext-Tiny.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny_w8a16.onnx) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
|
| 81 |
|
|
|
|
| 139 |
ConvNext-Tiny
|
| 140 |
Device : cs_8275 (ANDROID 14)
|
| 141 |
Runtime : TFLITE
|
| 142 |
+
Estimated inference time (ms) : 14.3
|
| 143 |
+
Estimated peak memory usage (MB): [0, 91]
|
| 144 |
Total # Ops : 328
|
| 145 |
Compute Unit(s) : npu (328 ops) gpu (0 ops) cpu (0 ops)
|
| 146 |
```
|