|
20 | 20 | LR = 0.02 # learning rate |
21 | 21 |
|
22 | 22 | # show data |
23 | | -steps = np.linspace(0, np.pi*2, 100, dtype=np.float32) |
24 | | -x_np = np.sin(steps)# float32 for converting torch FloatTensor |
| 23 | +steps = np.linspace(0, np.pi*2, 100, dtype=np.float32)# float32 for converting torch FloatTensor |
| 24 | +x_np = np.sin(steps) |
25 | 25 | y_np = np.cos(steps) |
26 | 26 | plt.plot(steps, y_np, 'r-', label='target (cos)') |
27 | 27 | plt.plot(steps, x_np, 'b-', label='input (sin)') |
@@ -77,8 +77,8 @@ def forward(self, x, h_state): |
77 | 77 | for step in range(100): |
78 | 78 | start, end = step * np.pi, (step+1)*np.pi # time range |
79 | 79 | # use sin predicts cos |
80 | | - steps = np.linspace(start, end, TIME_STEP, dtype=np.float32) |
81 | | - x_np = np.sin(steps)# float32 for converting torch FloatTensor |
| 80 | + steps = np.linspace(start, end, TIME_STEP, dtype=np.float32)# float32 for converting torch FloatTensor |
| 81 | + x_np = np.sin(steps) |
82 | 82 | y_np = np.cos(steps) |
83 | 83 |
|
84 | 84 | x = torch.from_numpy(x_np[np.newaxis, :, np.newaxis]) # shape (batch, time_step, input_size) |
|
0 commit comments