update reset

app.py

@@ -141,18 +141,17 @@ def draw_fig(ax, quantizer, data, title=""):
     ax.set_xticks(np.arange(-5, 11, 5))
     ax.set_yticks(np.arange(-10, 6, 5))
     ax.grid(linestyle='--', color='#333333', alpha=0.7)
-    ax.set_title(f"{title}", fontsize=26)
+    ax.set_title(f"{title}", fontsize=36)
 
 def draw_arrow(ax, start, end):
     for i in range(len(start)):
-        # 不用用plt.annotate
         ax.arrow(start[i][0], start[i][1], end[i][0] - start[i][0], end[i][1] - start[i][1],
                 head_width=0.1, head_length=0.1, fc='orange', ec='orange', alpha=0.8,
                 ls="-", lw=1)
 
 def draw_reset_result(num_data=16, num_code=12):
-    fig_reset, ax_reset = plt.subplots(1, 6, figsize=(36, 6), dpi=400)
-    fig_nreset, ax_nreset = plt.subplots(1, 6, figsize=(36, 6), dpi=400)
+    fig_reset, ax_reset = plt.subplots(1, 6, figsize=(72, 10), dpi=400)
+    fig_nreset, ax_nreset = plt.subplots(1, 6, figsize=(72, 10), dpi=400)
     x = torch.randn(num_data, 1) * 2 + 5
     y = torch.randn(num_data, 1) * 2 - 5
     data = torch.cat([x, y], dim=1)
@@ -162,8 +161,8 @@ def draw_reset_result(num_data=16, num_code=12):
     optimizer_nreset = torch.optim.SGD(quantizer_nreset.parameters(), lr=0.1)
     draw_fig(ax_reset[0], quantizer, data, title=f"Initialization")
     draw_fig(ax_nreset[0], quantizer_nreset, data, title=f"Initialization")
-    ax_reset[0].legend(["Data", "Code"], loc="upper right", fontsize=18)
-    ax_nreset[0].legend(["Data", "Code"], loc="upper right", fontsize=18)
+    ax_reset[0].legend(["Data", "Code"], loc="upper right", fontsize=24)
+    ax_nreset[0].legend(["Data", "Code"], loc="upper right", fontsize=24)
 
     i_list = [1, 3, 10, 50, 200]
 
@@ -288,21 +287,6 @@ if __name__ == "__main__":
         description="Upload an image to see how different VQ models (BaseVQ, VQGAN, ReVQ) reconstruct it from latent codes."
     )
 
-    # demo2 = gr.Interface(
-    #     fn=draw_process,
-    #     inputs=[
-    #         gr.Slider(label="x", value=0, minimum=-10, maximum=10, step=0.1),
-    #         gr.Slider(label="y", value=0, minimum=-10, maximum=10, step=0.1),
-    #         gr.Slider(label="std", value=1, minimum=0, maximum=5, step=0.1)
-    #     ],
-    #     outputs=[
-    #         gr.Image(label="NN", type="numpy"),
-    #         gr.Image(label="OptVQ", type="numpy")
-    #     ],
-    #     title="Demo 2: 2D Matching Visualization",
-    #     description="Visualize nearest neighbor vs. optimal transport matching for synthetic 2D data."
-    # )
-
     demo2 = gr.Interface(
         fn=draw_reset_result,  # 不再需要 handler 包装
         inputs=[