Update README.md
Browse files
README.md
CHANGED
|
@@ -34,14 +34,14 @@ In order to be robust to +/-1 star estimation errors, we will take the following
|
|
| 34 |
$$\mathrm{top\!-\!2\; acc}=\frac{1}{|\mathcal{O}|}\sum_{i\in\mathcal{O}}\sum_{0\leq l < 2}\mathbb{1}(\hat{f}_{i,l}=y_i)$$
|
| 35 |
where $\hat{f}_l$ is the l-th largest predicted label, $y$ the true label, $\mathcal{O}$ is the test set of the observations and $\mathbb{1}$ is the indicator function.
|
| 36 |
|
| 37 |
-
| **class** | **exact accuracy (%)** | **top-2 acc (%)** |
|
| 38 |
-
| :---------: | :--------------------: | :---------------: |
|
| 39 |
-
| **global** | 61.01 | 88.80 |
|
| 40 |
-
| **1 star** | 87.21 | 77.17 |
|
| 41 |
-
| **2 stars** | 79.19 | 84.75 |
|
| 42 |
-
| **3 stars** | 77.85 | 78.98 |
|
| 43 |
-
| **4 stars** | 78.61 | 90.22 |
|
| 44 |
-
| **5 stars** | 85.96 | 82.92 |
|
| 45 |
|
| 46 |
Benchmark
|
| 47 |
---------
|
|
|
|
| 34 |
$$\mathrm{top\!-\!2\; acc}=\frac{1}{|\mathcal{O}|}\sum_{i\in\mathcal{O}}\sum_{0\leq l < 2}\mathbb{1}(\hat{f}_{i,l}=y_i)$$
|
| 35 |
where $\hat{f}_l$ is the l-th largest predicted label, $y$ the true label, $\mathcal{O}$ is the test set of the observations and $\mathbb{1}$ is the indicator function.
|
| 36 |
|
| 37 |
+
| **class** | **exact accuracy (%)** | **top-2 acc (%)** | **support** |
|
| 38 |
+
| :---------: | :--------------------: | :---------------: | :---------: |
|
| 39 |
+
| **global** | 61.01 | 88.80 | 9,698 |
|
| 40 |
+
| **1 star** | 87.21 | 77.17 | 1,905 |
|
| 41 |
+
| **2 stars** | 79.19 | 84.75 | 1,935 |
|
| 42 |
+
| **3 stars** | 77.85 | 78.98 | 1,974 |
|
| 43 |
+
| **4 stars** | 78.61 | 90.22 | 1,952 |
|
| 44 |
+
| **5 stars** | 85.96 | 82.92 | 1,932 |
|
| 45 |
|
| 46 |
Benchmark
|
| 47 |
---------
|